模型 · Pirate Face

Qwen3.8

3个月前发布27B2446BFlash-Next 180B 1.0k

27B543 个上传 · 🧲 311 · 75M ↓

16-bit56 GB 72 Other~57 GB 0 8-bit31 GB 3 6-bit23 GB 1 5-bit19 GB 1 4-bit18 GB 8 3-bit15 GB 0 2-bit8.6 GB 4 1-bit~3.5 GB 3 GGUF~17 GB 4

查看其余 533 个上传项

huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUFGGUF 5
lmstudio-community/Qwen3.8-27B-MLX-4bit4-bit 3
lmstudio-community/Qwen3.8-27B-MLX-8bit8-bit 1
JonathanColetti/Qwen3.8-27B-Uncensored-GGUFGGUF 22
HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUFGGUF 10
byteshape/Qwen3.8-27B-GGUFGGUF 14
unsloth/Qwen3.8-27B-NVFP4NVFP4 4
prism-ml/Ternary-Bonsai-2-27B-ggufGGUF 8
autotrust/JEV-27B-VLFull 1
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUFGGUF 6
peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUFGGUF 0
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUFGGUF 19
显示 12 / 533 个

2446B激活 95B1 个上传 · 🧲 1 · 26k ↓

16-bit4.9 TB 1

社区版本 · 65 个上传

Qwen3.8 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

empero-ai/Qwen3.8-35B-A3B-Distill-GGUF35B · GGUF 6
empero-ai/Qwen3.8-2B-Distill-GGUF2B · GGUF 3
IsValorum/Qwen3.8-35B-A3B-Distill-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF35B · GGUF 2
mradermacher/Qwen3.8-9B-Distill-uncensored-heretic-GGUF9B · GGUF 2
mradermacher/Qwen3.8-14B-Instruct-Turbo-GGUF14B · GGUF 0
mradermacher/Qwen3.8-9B-heretic-uncensored-GGUF9B · GGUF 2
Noobito45/Qwen3.8-9B-heretic-uncensored-NVFP4-GGUF9B · NVFP4 1
DavidAU/LFM2.5-8B-A1B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF8B · GGUF 0
DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF2.6B · GGUF 3
JetBrains/Qwen3.8-3.6-27B-blend-GGUF27B · GGUF 3
ge525/Qwen3.8-9B-Distill-uncensored-heretic-Q4_K_M-GGUF9B · Q4_K_M 1
mradermacher/Qwen3.8-cyber-RedTeam-Surgical-Abliterated-GGUFGGUF 0
显示 12 / 65 个

Flash-Next 180B92 个上传 · 🧲 42 · 24M ↓

16-bit360 GB 0 Other~378 GB 0 8-bit186 GB 0 4-bit129 GB 0 3-bit90 GB 4 2-bit~47 GB 1-bit~24 GB GGUF~113 GB 8

查看其余 84 个上传项

Flash-Next · 社区版本 · 17 个上传

Qwen3.8-Flash-Next 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

incoai/Qwen3.8-Flash-Next-DFlash2600M · Full 3
0xKitkat/Qwen3.8-Flash-Next-125B-UltraLite-37GiB-GGUF125B · GGUF 0
local-inference-lab/Qwen3.8-Flash-Next-NVFP493B · NVFP4
mazinb/Qwen3.8-Flash-Next-Uncensored-NVFP4120B · NVFP4
dealignai/Qwen3.8-Flash-Next-CYBERSECURITY-NVFP4120B · NVFP4
butterf1ying/Qwen3.8-Flash-Next-Uncensored-REAP288-MTP-MLX-4bit79B · 4-bit
Mia-AiLab/Qwen3.8-Flash-Next-NVFP493B · NVFP4
ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw98B · Full
Jab1718/qwen3.8-flash-coder-85gb-bf1643B · BF16
halt95/Qwen3.8-Flash-Next-W4A16-Merlin124B · INT4
inference-optimization/Qwen3.8-Flash-Next-0.2B-A0.2B0.2B · Full
thousandml/Qwen3.8-Flash-Next-CQ-4bit1.5B · 4-bit
显示 12 / 17 个

Qwen3.6

7个月前发布27B35B 176

27B130 个上传 · 🧲 51 · 11M ↓

16-bit56 GB 3 Other~57 GB 8-bit31 GB 1 6-bit23 GB 0 5-bit19 GB 0 4-bit19 GB 0 2-bit~7.1 GB 1 1-bit5.2 GB 3 GGUF~17 GB 15

查看其余 121 个上传项

lmstudio-community/Qwen3.6-27B-MLX-4bit4-bit 0
lmstudio-community/Qwen3.6-27B-MLX-8bit8-bit 0
unsloth/Qwen3.6-27B-NVFP4NVFP4 1
nvidia/Qwen3.6-27B-NVFP4NVFP4 14
prism-ml/Ternary-Bonsai-27B-ggufGGUF 0
unsloth/Qwen3.6-27B-GGUFGGUF 5
prism-ml/Bonsai-27B-ggufGGUF 6
cyankiwi/Qwen3.6-27B-AWQ-INT4INT4 1
z-lab/Qwen3.6-27B-DFlashFull 1
batiai/Qwen3.6-27B-GGUFGGUF 0
unsloth/Qwen3.6-27B-MTP-GGUFGGUF 1
HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-AggressiveGGUF 0
显示 12 / 121 个

35B激活 3B157 个上传 · 🧲 60 · 30M ↓

16-bit72 GB 7 Other~74 GB 8-bit37 GB 1 6-bit~28 GB 0 5-bit28 GB 4-bit23 GB 6 3-bit~14 GB 2-bit13 GB 0 GGUF~22 GB 6

查看其余 148 个上传项

unsloth/Qwen3.6-35B-A3B-MTP-GGUFGGUF 1
unsloth/Qwen3.6-35B-A3B-GGUFGGUF 3
RedHatAI/Qwen3.6-35B-A3B-NVFP4NVFP4 1
unsloth/Qwen3.6-35B-A3B-NVFP4-FastNVFP4 6
unsloth/Qwen3.6-35B-A3B-NVFP4NVFP4 1
Bahushruth/Qwen3.6-35B-A3B-abliterated-v4Full 5
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUFGGUF 10
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-GGUFGGUF 7
QuantTrio/Qwen3.6-35B-A3B-AWQAWQ 6
lmstudio-community/Qwen3.6-35B-A3B-MLX-4bit4-bit 0
lmstudio-community/Qwen3.6-35B-A3B-MLX-8bit8-bit 0
bartowski/Qwen_Qwen3.6-35B-A3B-GGUFGGUF 0
显示 12 / 148 个

社区版本 · 31 个上传

Qwen3.6 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

Qwen3.5

8个月前发布0.8B2B4B9B27B35B122B397B 511

0.8B86 个上传 · 🧲 64 · 5.8M ↓

16-bit1.8 GB 4 Other1.0 GB 8-bit1.0 GB 0 6-bit632 MB 0 4-bit~420 MB 0 2-bit~210 MB GGUF~504 MB 0

查看其余 79 个上传项

Qwen/Qwen3.5-0.8B-BaseFull 1
unsloth/Qwen3.5-0.8B-GGUFGGUF 1
ATH-MaaS/OvisOCR3Full 4
unsloth/Qwen3.5-0.8BFull 0
Hcompany/Holo-3.1-35B-A3B-GGUFGGUF 0
ATH-MaaS/OvisOCR2Full 4
ggml-org/Qwen3.5-0.8B-GGUFGGUF 0
onnx-community/Qwen3.5-0.8B-ONNX 0
bartowski/Qwen_Qwen3.5-0.8B-GGUFGGUF 2
xiaomi-research/Xiaomi-OCR-0Full 6
SeerRay-Lab/Xiaomi-OCR-0Full 10
weareapexcreators/Qwen3.5-0.8B-LocalAIGGUF 0
显示 12 / 79 个

2B93 个上传 · 🧲 53 · 6.5M ↓

16-bit4.6 GB 3 Other~4.2 GB 8-bit2.7 GB 0 6-bit~1.6 GB 2 4-bit~1.1 GB 0 2-bit~525 MB 0 GGUF~1.3 GB 0

查看其余 86 个上传项

unsloth/Qwen3.5-2B-GGUFGGUF 2
Qwen/Qwen3.5-2B-BaseFull 5
Alibaba-DAMO-Academy/RynnBrain1.1-2BFull 0
turintech/Qwen3.5-2B-Artemis-GGUFGGUF 4
unsloth/Qwen3.5-2BFull 0
HauhauCS/Qwen3.5-2B-Uncensored-HauhauCS-AggressiveGGUF 2
bartowski/Qwen_Qwen3.5-2B-GGUFGGUF 1
openbmb/MiniCPM-OCR-JevFull 1
unsloth/Qwen3.5-2B-MTP-GGUFGGUF 0
Jackrong/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled-GGUFGGUF 0
mradermacher/Huihui-Qwen3.5-2B-abliterated-GGUFGGUF 1
weareapexcreators/Qwen3.5-2B-MTP-LocalAIGGUF 1
显示 12 / 86 个

4B162 个上传 · 🧲 93 · 10M ↓

16-bit9.3 GB 6 Other~8.4 GB 8-bit~4.2 GB 0 4-bit~2.1 GB 0 2-bit~1.1 GB 0 GGUF~2.5 GB 0

查看其余 156 个上传项

Qwen/Qwen3.5-4B-BaseFull 1
ccore/Qwen3.5-4B-3D-CoderGGUF 1
HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-AggressiveGGUF 11
turintech/Qwen3.5-4B-Artemis-GGUFGGUF 0
lmstudio-community/Qwen3.5-4B-GGUFGGUF 4
unsloth/Qwen3.5-4BFull 0
empero-ai/Qwen3.8-4B-DistillFull 0
alibiserikbay/JevK5Full 0
cyankiwi/Qwen3.5-4B-AWQ-4bitAWQ 3
bartowski/Qwen_Qwen3.5-4B-GGUFGGUF 1
prism-ml/Ternary-Bonsai-2-4B-ggufGGUF 0
unsloth/Qwen3.5-4B-MTP-GGUFGGUF 1
显示 12 / 156 个

9B287 个上传 · 🧲 92 · 18M ↓

16-bit19 GB 3 8-bit10 GB 1 4-bit6.0 GB 4 2-bit~2.4 GB 0 GGUF~5.7 GB 18

查看其余 282 个上传项

unsloth/Qwen3.5-9B-GGUFGGUF 3
prism-ml/Ternary-Bonsai-2-9B-ggufGGUF 1
mradermacher/Qwen3.5-9B-Kimi-k3-Distilled-GGUFGGUF 0
lmstudio-community/Qwen3.5-9B-GGUFGGUF 3
HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-AggressiveGGUF 5
mradermacher/Huihui-Qwen3.5-9B-abliterated-GGUFGGUF 2
Qwen/Qwen3.5-9B-BaseFull 6
mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUFGGUF 0
mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUFGGUF 10
cyankiwi/Qwen3.5-9B-AWQ-4bitAWQ 0
bartowski/Qwen_Qwen3.5-9B-GGUFGGUF 2
Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUFGGUF 3
显示 12 / 282 个

27B47 个上传 · 🧲 15 · 2.9M ↓

16-bit56 GB 6 Other~57 GB 8-bit31 GB 0 4-bit~14 GB 0 2-bit~7.1 GB GGUF~17 GB 0

查看其余 41 个上传项

bartowski/Qwen_Qwen3.5-27B-GGUFGGUF 0
huihui-ai/Huihui-Qwen3.5-27B-abliteratedFull 0
QuantTrio/Qwen3.5-27B-AWQAWQ 0
z-lab/Qwen3.5-27B-DFlashFull 3
coder3101/Qwen3.5-27B-hereticFull 2
Nianchen/IndustryForge-27BFull 0
THUSI-Lab/GameScaling-27B-S3Full 1
llmfan46/Qwen3.5-27B-uncensored-heretic-v1Full 0
groxaxo/Code-Writer-V2-Obliterated-BF16BF16 0
neigezhu/qwen3.5-27b-jailbreak-v5-last16Full 0
groxaxo/Code-Writer-V2-ObliteratedFull 0
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUFGGUF
显示 12 / 41 个

35B激活 3B37 个上传 · 🧲 11 · 3.9M ↓

16-bit72 GB 9 8-bit37 GB 5 4-bit~18 GB 0 3-bit~14 GB 2-bit~9.2 GB GGUF~22 GB 6

查看其余 31 个上传项

HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-AggressiveGGUF 0
Qwen/Qwen3.5-35B-A3B-BaseFull 0
bartowski/Qwen_Qwen3.5-35B-A3B-GGUFGGUF 0
apodex/Apodex-1.1-miniFull 0
huihui-ai/Huihui-Qwen3.5-35B-A3B-abliteratedFull 1
z-lab/Qwen3.5-35B-A3B-DFlashFull 0
Smoffyy/Qwen3.5-35B-A3B-Instruct-Pure-GGUFGGUF 7
QuantTrio/Qwen3.5-35B-A3B-AWQAWQ
mradermacher/Huihui-Qwen3.5-35B-A3B-abliterated-GGUFGGUF
cyankiwi/Qwen3.5-35B-A3B-AWQ-4bitAWQ
mradermacher/Gemini-3-Pro-Qwen3.5-35B-A3B-i1-GGUFGGUF
cesarsal1nas/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated-Q4_K_M-GGUFQ4_K_M
显示 12 / 31 个

122B激活 10B23 个上传 · 🧲 8 · 1.9M ↓

16-bit250 GB 6 8-bit127 GB 0 4-bit79 GB 0 2-bit~32 GB GGUF~77 GB 5

查看其余 18 个上传项

nvidia/Qwen3.5-122B-A10B-NVFP4NVFP4 13
z-lab/Qwen3.5-122B-A10B-DFlashFull 0
mradermacher/Qwen3.5-122B-A10B-abliterated-v1-GGUFGGUF 0
isilicon/mango-qwen35-122b-q4Q4 0
unsloth/Qwen3.5-122B-A10B-GGUFGGUF
llmfan46/Qwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUFGGUF
huihui-ai/Huihui-Qwen3.5-122B-A10B-abliterated-GGUFGGUF
cyankiwi/Qwen3.5-122B-A10B-AWQ-4bitAWQ
BAAI/AREX-BaseFull
QuantTrio/Qwen3.5-122B-A10B-AWQAWQ
Thaurock/Qwen3.5-122B-A10B-abliterated-GGUFGGUF
wangzhang/Qwen3.5-122B-A10B-abliterated-GGUFGGUF
显示 12 / 18 个

397B激活 17B13 个上传 · 🧲 3 · 1.0M ↓

16-bit807 GB 0 8-bit406 GB 0 4-bit251 GB 6 GGUF~250 GB

查看其余 9 个上传项

社区版本 · 18 个上传

Qwen3.5 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

optimum-intel-internal-testing/tiny-random-qwen3.5-moe16M · Full 3
optimum-intel-internal-testing/tiny-random-qwen3.5-moe-mtpFull 0
optimum-intel-internal-testing/tiny-random-qwen3.5-mtpFull 1
optimum-intel-internal-testing/tiny-random-qwen3.516M · Full 0
optimum-intel-internal-testing/tiny-random-qwen3.5-compressed-tensors16M · Full 0
brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF14B · Q4_K_M 0
tvall43/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-gguf14B · GGUF 0
llmfan46/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-uncensored-heretic-GGUF40B · GGUF 0
FrosT-LyRo/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-i1-GGUF40B · GGUF
mradermacher/Crow-9B-Opus-4.6-Distill-Heretic_Qwen3.5-i1-GGUF9B · GGUF
mradermacher/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-i1-GGUF40B · GGUF
mradermacher/Qwen3.5-40B-RoughHouse-Claude-4.6-Opus-Polar-Deckard-Uncensored-Heretic-Thinking-i1-GGUF40B · GGUF
显示 12 / 18 个

Qwen3

2年前发布0.6B1.7B4B8B14B32B235BCoder 30BCoder 480BCoder-Next 80BNext 80BOmni 30BVL 2BVL 4BVL 8BVL 30BVL 235B 440

0.6B97 个上传 · 🧲 68 · 24M ↓

16-bit1.5 GB 14 8-bit~630 MB 5 6-bit~473 MB 0 4-bit~315 MB 4 2-bit~158 MB GGUF~378 MB 0

查看其余 91 个上传项

PrimeIntellect/Qwen3-0.6BFull 1
Qwen/Qwen3-0.6B-BaseFull 1
Qwen/Qwen3Guard-Gen-0.6BFull 6
Qwen/Qwen3-Embedding-0.6B-GGUFGGUF 0
unsloth/Qwen3-0.6B-GGUFGGUF 1
litert-community/Qwen3-0.6B 0
Qwen/Qwen3-0.6B-FP8FP8 1
ggml-org/Qwen3-0.6B-GGUFGGUF 0
mradermacher/qwen3-0.6b-abliterated-i1-GGUFGGUF 0
mlx-community/Qwen3-0.6B-4bit4-bit 0
mlx-community/Qwen3-0.6B-8bit8-bit 0
mlx-community/Qwen3-Embedding-0.6B-4bit-DWQ4-bit 0
显示 12 / 91 个

1.7B72 个上传 · 🧲 45 · 9.3M ↓

16-bit4.1 GB 4 8-bit1.8 GB 1 6-bit1.4 GB 0 4-bit~893 MB 0 2-bit~446 MB GGUF~1.1 GB 1

查看其余 66 个上传项

Qwen/Qwen3-TTS-12Hz-1.7B-BaseFull 3
Qwen/Qwen3-1.7B-BaseFull 4
PrimeIntellect/Qwen3-1.7BFull 0
Qwen/Qwen3-1.7B-GGUFGGUF 0
ggml-org/Qwen3-1.7B-GGUFGGUF 2
tobil/qmd-query-expansion-1.7B-ggufGGUF 2
ggml-org/Qwen3-TTS-12Hz-1.7B-Base-GGUFGGUF 0
litert-community/Qwen3-1.7B 0
lmstudio-community/Qwen3-1.7B-MLX-4bit4-bit 0
lmstudio-community/Qwen3-1.7B-MLX-bf16BF16 0
mlx-community/Qwen3-1.7B-4bit4-bit 0
Qwen/Qwen3-1.7B-FP8FP8 4
显示 12 / 66 个

4B153 个上传 · 🧲 78 · 12M ↓

16-bit8.1 GB 5 8-bit5.2 GB 1 6-bit3.3 GB 0 5-bit2.8 GB 0 4-bit~2.1 GB 1 2-bit~1.1 GB GGUF~2.5 GB 1

查看其余 146 个上传项

Qwen/Qwen3-4B-Instruct-2507Full 1
Qwen/Qwen3-4B-GGUFGGUF 1
unsloth/Qwen3-4B-GGUFGGUF 1
Qwen/Qwen3-4B-BaseFull 1
Qwen/Qwen3-4B-Thinking-2507Full 4
AnkitAI/Parable-Qwen3-4B-Claude-Fable-5-GGUFGGUF 1
Qwen/Qwen3-4B-AWQAWQ 1
mlx-community/Qwen3-4B-Instruct-2507-4bit4-bit 0
llmat/Qwen3-4B-Instruct-2507-NVFP4NVFP4 1
Qwen/Qwen3-4B-FP8FP8 1
llamafactory/tiny-random-qwen3Full 1
Qwen/Qwen3-Embedding-4B-GGUFGGUF 0
显示 12 / 146 个

8B118 个上传 · 🧲 53 · 12M ↓

16-bit16 GB 4 Other~17 GB 8-bit9.5 GB 1 4-bit6.1 GB 1 2-bit~2.1 GB GGUF~5.0 GB 3

查看其余 112 个上传项

Qwen/Qwen3-8B-BaseFull 4
deepseek-ai/DeepSeek-R1-0528-Qwen3-8BFull 3
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit4-bit 1
AnkitAI/Parable-Qwen3-8B-Claude-Fable-5-GGUFGGUF 1
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-8bit8-bit 1
unsloth/Qwen3-8B-unsloth-bnb-4bit4-bit 0
unsloth/Qwen3-8B-GGUFGGUF 0
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUFGGUF 0
nvidia/Qwen3-8B-NVFP4NVFP4 3
Qwen/Qwen3Guard-Gen-8BFull 0
mradermacher/Huihui-Qwen3-8B-abliterated-v2-GGUFGGUF 2
lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-GGUFGGUF 0
显示 12 / 112 个

14B56 个上传 · 🧲 22 · 16M ↓

16-bit30 GB 1 8-bit16 GB 0 6-bit12 GB 0 5-bit10 GB 4-bit10.0 GB 1 2-bit~3.7 GB GGUF~8.8 GB 0

查看其余 49 个上传项

unsloth/Qwen3-14B-unsloth-bnb-4bit4-bit 0
Qwen/Qwen3-14B-BaseFull 3
unsloth/Qwen3-14B-GGUFGGUF 0
lmstudio-community/Qwen3-14B-MLX-4bit4-bit 0
nvidia/Qwen3-14B-NVFP4NVFP4 1
unsloth/Qwen3-14B-bnb-4bit4-bit 2
NousResearch/Hermes-4-14BFull 0
HuggingFaceBio/Carbon-XFull 3
Qwen/Qwen3-14B-MLX-4bit4-bit 0
ijohn07/Qwen3-14B-Uncensored-Q4_K_M-GGUFQ4_K_M 2
togethercomputer/HybridAgent-14B-AgenticFull 0
microsoft/FrogMini-14B-2510Full 0
显示 12 / 49 个

32B59 个上传 · 🧲 18 · 7.0M ↓

16-bit66 GB 1 8-bit31 GB 0 4-bit19 GB 3 2-bit~8.4 GB GGUF~20 GB 0

查看其余 54 个上传项

Qwen/Qwen3-30B-A3BFull 6
Qwen/Qwen3-30B-A3B-Instruct-2507Full 27
YuYu1015/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-NVFP4NVFP4 1
Qwen/Qwen3-30B-A3B-GGUFGGUF 0
Qwen/Qwen3-32B-GGUFGGUF 0
cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bitAWQ 0
RedHatAI/Qwen3-32B-NVFP4NVFP4 0
stelterlab/Qwen3-30B-A3B-Instruct-2507-AWQAWQ 0
Qwen/Qwen3-30B-A3B-Thinking-2507Full 2
Qwen/Qwen3-32B-FP8FP8 0
Qwen/Qwen3-30B-A3B-FP8FP8 0
inference-optimization/Qwen3-1.6B-A0.9BFull 0
显示 12 / 54 个

235B激活 22B7 个上传 · 🧲 3 · 439k ↓

16-bit470 GB 1 8-bit236 GB 0 4-bit~123 GB

查看其余 4 个上传项

社区版本 · 27 个上传

Qwen3 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

optimum-intel-internal-testing/tiny-random-qwen3-deepspec-dflashFull 3
software-mansion/react-native-executorch-qwen-3 0
optimum-intel-internal-testing/tiny-random-qwen3-ttsFull 0
PrimeIntellect/qwen3-moe-tiny670M · Full 2
cstr/qwen3-tts-voices-GGUFGGUF 1
Mostafa8Mehrabi/qwen3-71M-c4-final50M · Full 1
amd/tiny-qwen3-moe-w8a8-int8740M · INT8 0
Adamji/tiny-qwen3-moe-fp8-per-block20M · FP8 0
Mostafa8Mehrabi/qwen3-30m-tinystories-final30M · Full 1
KVCache-ai/Qwen3-30BA3B-GGUFGGUF 0
vllm-project/tiny-qwen3-moe-fp8-per-block20M · FP8 0
DavidAU/Qwen3-Zero-Coder-Reasoning-V2-0.8B-NEO-EX-GGUF0.8B · GGUF
显示 12 / 27 个

Coder 30B激活 3B30 个上传 · 🧲 16 · 4.3M ↓

16-bit61 GB 0 8-bit31 GB 2 6-bit25 GB 0 5-bit21 GB 0 4-bit~16 GB 1 GGUF~19 GB 1

查看其余 24 个上传项

Coder 480B激活 35B4 个上传 · 🧲 1 · 96k ↓

16-bit~1.0 TB 8-bit482 GB 6 4-bit~252 GB

查看其余 1 个上传项

QuantTrio/Qwen3-Coder-480B-A35B-Instruct-GPTQ-Int4-Int8MixINT4

Coder-Next 80B13 个上传 · 🧲 10 · 1.4M ↓

16-bit159 GB 0 8-bit80 GB 2 6-bit65 GB 0 4-bit45 GB 0 GGUF~50 GB 0

查看其余 8 个上传项

Coder-Next · 社区版本 · 3 个上传

Qwen3-Coder-Next 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

thousandml/Qwen3-Coder-Next-CQ-4bit750M · 4-bit 0
cyankiwi/Qwen3-Coder-Next-AWQ-4bit14B · AWQ
textclf/Qwen3-Coder-Next-TQ-4bit750M · 4-bit

Next 80B激活 3B8 个上传 · 🧲 5 · 191k ↓

16-bit163 GB 0 8-bit82 GB 0 4-bit49 GB GGUF~50 GB 0

查看其余 4 个上传项

Omni 30B激活 3B9 个上传 · 🧲 6 · 533k ↓

16-bit71 GB 0 4-bit~16 GB 1

查看其余 7 个上传项

VL 2B19 个上传 · 🧲 16 · 1.5M ↓

16-bit4.3 GB 3 8-bit~2.1 GB 0 4-bit~1.1 GB 0 GGUF~1.3 GB 8

查看其余 15 个上传项

unsloth/Qwen3-VL-2B-Instruct-GGUFGGUF 0
Qwen/Qwen3-VL-2B-ThinkingFull 0
mobilint/Qwen3-VL-2B-InstructFull 0
typhoon-ai/typhoon-ocr1.5-2bFull 1
cyankiwi/Qwen3-VL-2B-Instruct-AWQ-4bitAWQ 1
Qwen/Qwen3-VL-2B-Thinking-FP8FP8 0
inclusionAI/ZwZ-2BFull 0
unsloth/Qwen3-VL-2B-Instruct-bnb-4bit4-bit 0
MTalha2001/LOCUS-2BFull 0
taobao-mnn/Qwen3-VL-2B-Instruct-Eagle3Full 1
opendatalab/ChartVerse-2BFull 1
zeromodels/qwen3-vl-2b-thinking 0
显示 12 / 15 个

VL 4B31 个上传 · 🧲 21 · 5.4M ↓

16-bit8.9 GB 2 8-bit6.0 GB 3 6-bit4.1 GB 0 5-bit3.6 GB 1 4-bit3.1 GB 1 GGUF~2.5 GB 2

查看其余 25 个上传项

unsloth/Qwen3-VL-4B-Instruct-GGUFGGUF 2
lmstudio-community/Qwen3-VL-4B-Instruct-MLX-8bit8-bit 1
Hcompany/Holo2-4BFull 0
unsloth/Qwen3-VL-4B-InstructFull 0
mlx-community/Qwen3-VL-4B-Instruct-4bit4-bit 2
Qwen/Qwen3-VL-4B-ThinkingFull 2
unsloth/Qwen3-VL-4B-Instruct-unsloth-bnb-4bit4-bit 2
huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliteratedFull 2
cyankiwi/Qwen3-VL-4B-Instruct-AWQ-4bitAWQ 0
guanxuyu/visual-jev-4b-answer-sftFull 0
unsloth/Qwen3-VL-4B-Instruct-bnb-4bit4-bit 5
cyankiwi/Qwen3-VL-4B-Instruct-AWQ-8bitAWQ 0
显示 12 / 25 个

VL 8B42 个上传 · 🧲 25 · 12M ↓

16-bit18 GB 3 8-bit11 GB 3 6-bit7.8 GB 2 5-bit6.8 GB 3 4-bit~4.2 GB 1 GGUF~5.0 GB 1

查看其余 36 个上传项

mradermacher/Qwen3-VL-8B-Instruct-abliterated-GGUFGGUF 7
unsloth/Qwen3-VL-8B-Instruct-GGUFGGUF 0
Qwen/Qwen3-VL-8B-ThinkingFull 0
lmstudio-community/Qwen3-VL-8B-Instruct-MLX-4bit4-bit 0
lmstudio-community/Qwen3-VL-8B-Instruct-MLX-8bit8-bit 0
HauhauCS/Qwen3VL-8B-Uncensored-HauhauCS-AggressiveGGUF 1
unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit4-bit 0
huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliteratedFull 3
SherlockID365/Qwen3-VL-8B-Instruct-quantized.w4a16INT4 0
mlx-community/Qwen3-VL-8B-Instruct-4bit4-bit 0
pottokao/Qwen-Image-2.1-Text-Encoder-HereticFull 3
microsoft/AesCode-8BFull 0
显示 12 / 36 个

VL 30B激活 3B28 个上传 · 🧲 11 · 1.7M ↓

16-bit62 GB 11 8-bit36 GB 0 4-bit21 GB 0 GGUF~19 GB 0

查看其余 24 个上传项

Qwen/Qwen3-VL-30B-A3B-Instruct-FP8FP8 1
Qwen/Qwen3-VL-32B-InstructFull 0
QuantTrio/Qwen3-VL-30B-A3B-Instruct-AWQAWQ 1
cyankiwi/Qwen3-VL-30B-A3B-Instruct-AWQ-4bitAWQ 0
Raretutor/Qwen3-VL-32B-MiniMax-H3-GGUFGGUF 2
cyankiwi/Qwen3-VL-32B-Instruct-AWQ-8bitAWQ 0
ethanfel/Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRotINT8 0
nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUFGGUF
pottokao/MiniMax-H3-TextEncoder-Qwen3VL-32B-abliterated-GGUFGGUF
QuantTrio/Qwen3-VL-30B-A3B-Thinking-AWQAWQ
unsloth/Qwen3-VL-30B-A3B-Thinking-GGUFGGUF
Qwen/Qwen3-VL-32B-Thinking-GGUFGGUF
显示 12 / 24 个

VL 235B激活 22B5 个上传 · 🧲 1 · 328k ↓

16-bit471 GB 0 8-bit223 GB 4-bit~123 GB

查看其余 2 个上传项

VL · 社区版本 · 4 个上传

Qwen3-VL 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

QwQ

2年前发布32B 0

32B7 个上传 · 🧲 2 · 40k ↓

16-bit66 GB 4-bit20 GB 3-bit14 GB 2-bit12 GB GGUF~20 GB 0

查看其余 2 个上传项

社区版本 · 7 个上传

QwQ 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

mradermacher/QwQ-0.5B-Distilled-SFT-GGUF0.5B · GGUF 0
mradermacher/ewre324-QwQ-0.5B-Distilled-SFT-Reason-GGUF0.5B · GGUF 0
Novaciano/QwQ-0.5B-Distilled_and_Uncensored-GGUF0.5B · GGUF 0
mradermacher/QwQ-0.5B-Distilled-GGUF0.5B · GGUF 0
Cran-May/QwQ-0.5B-Distilled-SFT-Q5_K_M-GGUF0.5B · Q5_K_M 0
NikolayKozloff/QwQ-0.5B-Distilled-SFT-Q8_0-GGUF0.5B · Q8_0 0
itlwas/QwQ-0.5B-Distilled-SFT-Q4_K_M-GGUF0.5B · Q4_K_M 0

Qwen2.5

2年前发布0.5B1.5B7B14B32BCoder 0.5BCoder 1.5BCoder 7BCoder 14BCoder 32BMath 1.5BMath 7BVL 7BVL 32B 267

0.5B105 个上传 · 🧲 82 · 6.4M ↓

16-bit1000 MB 3 Other969 MB 8-bit~525 MB 2 4-bit~263 MB 1 GGUF~315 MB 3

查看其余 100 个上传项

Qwen/Qwen2.5-0.5BFull 3
bartowski/Qwen2.5-0.5B-Instruct-GGUFGGUF 4
mlx-community/Qwen2.5-0.5B-Instruct-4bit4-bit 0
Qwen/Qwen2.5-Coder-0.5BFull 1
unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit4-bit 0
lmstudio-community/Qwen2.5-0.5B-Instruct-MLX-4bit4-bit 0
unsloth/Qwen2.5-0.5B-unsloth-bnb-4bit4-bit 0
sallani/EUAIAct-Qwen2.5-0.5B-EdgeGGUF 0
unsloth/Qwen2.5-0.5BFull 1
sallani/ISO27001-Qwen2.5-0.5B-EdgeGGUF 0
Qwen/Qwen2.5-0.5B-Instruct-AWQAWQ 1
Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4INT4 2
显示 12 / 100 个

1.5B51 个上传 · 🧲 32 · 7.2M ↓

16-bit3.1 GB 4 8-bit2.2 GB 1 4-bit~788 MB 3 GGUF~945 MB 11

查看其余 47 个上传项

Qwen/Qwen2.5-1.5BFull 3
Qwen/Qwen2.5-Coder-1.5BFull 1
Qwen/Qwen2.5-Math-1.5BFull 1
JackKozmo29/depguard-jev-style-1.5bFull 0
JackKozmo29/sevclassifier-jev-style-1.5bFull 2
JackKozmo29/mailguard-jev-style-1.5bFull 0
JackKozmo29/codeguard-jev-style-1.5bFull 0
unsloth/Qwen2.5-1.5B-unsloth-bnb-4bit4-bit 0
unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit4-bit 0
Qwen/Qwen2.5-1.5B-Instruct-AWQAWQ 3
mlx-community/Qwen2.5-1.5B-Instruct-4bit4-bit 0
unsloth/Qwen2.5-1.5BFull 1
显示 12 / 47 个

7B73 个上传 · 🧲 38 · 10M ↓

16-bit15 GB 13 8-bit8.7 GB 2 5-bit5.4 GB 4-bit~3.7 GB 1 GGUF~4.4 GB 0

查看其余 68 个上传项

Qwen/Qwen2.5-7BFull 1
Qwen/Qwen2.5-Coder-7BFull 1
bartowski/Qwen2.5-7B-Instruct-GGUFGGUF 2
unsloth/Qwen2.5-7B-InstructFull 0
Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4INT4 6
unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit4-bit 0
Qwen/Qwen2.5-7B-Instruct-1MFull 0
unsloth/Qwen2.5-7B-Instruct-bnb-4bit4-bit 0
Qwen/Qwen2.5-Math-7BFull 3
LocalAI-io/LocalAI-functioncall-qwen2.5-7b-v0.5-Q4_K_M-GGUFQ4_K_M 0
mlx-community/Qwen2.5-7B-Instruct-4bit4-bit 7
paultimothymooney/Qwen2.5-7B-Instruct-Q4_K_M-GGUFQ4_K_M 0
显示 12 / 68 个

14B32 个上传 · 🧲 14 · 2.3M ↓

16-bit30 GB 17 8-bit16 GB 4-bit10.0 GB 1 GGUF~8.8 GB 1

查看其余 28 个上传项

Qwen/Qwen2.5-14BFull 0
Qwen/Qwen2.5-14B-Instruct-GGUFGGUF 0
unsloth/Qwen2.5-14B-Instruct-bnb-4bit4-bit 0
unsloth/Qwen2.5-14B-bnb-4bit4-bit 2
Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4INT4 0
TheRains/Qwen2.5-14B-Instruct-Q4_K_M-GGUFQ4_K_M 0
Qwen/Qwen2.5-Coder-14BFull 0
TouchNight/Qwen2.5-14B_Uncencored-Q4_K_M-GGUFQ4_K_M 0
ByteDance-Seed/AHN-Mamba2-for-Qwen-2.5-Instruct-14BFull 1
ByteDance-Seed/AHN-GDN-for-Qwen-2.5-Instruct-14BFull 1
ByteDance-Seed/AHN-DN-for-Qwen-2.5-Instruct-14BFull 1
bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUFGGUF
显示 12 / 28 个

32B20 个上传 · 🧲 5 · 2.9M ↓

16-bit66 GB 6 8-bit35 GB 0 4-bit19 GB 1 GGUF~20 GB 6

查看其余 16 个上传项

社区版本 · 33 个上传

Qwen2.5 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit3B · 4-bit 0
unsloth/Qwen2.5-3B-Instruct-bnb-4bit3B · 4-bit 2
mradermacher/Qwen2.5-3B-Instruct-abliterated-GGUF3B · GGUF 0
software-mansion/react-native-executorch-qwen-2.5 0
unsloth/Qwen2.5-3B-unsloth-bnb-4bit3B · 4-bit 0
moonshotai/Kimi-Dev-72B72B · Full 0
vinguyen0891/Vivy-R-Vision-3B-GGUF3B · GGUF 1
vinguyen0891/Vivy-R-Robotics-3B-GGUF3B · GGUF 1
tensorblock/Qwen2.5-3B-Instruct-Uncensored-Test-GGUF3B · GGUF 0
vinguyen0891/Vivy-R-Finance-3B-GGUF3B · GGUF 1
zemelee/qwen2.5-jailbreak3B · Full 0
mithra99/qwen-2.5-distilled-sft-8bit8-bit 0
显示 12 / 33 个

Coder 0.5B14 个上传 · 🧲 13 · 160k ↓

16-bit988 MB 1 8-bit651 MB 0 4-bit~263 MB 0 GGUF~315 MB 0

查看其余 10 个上传项

Coder 1.5B23 个上传 · 🧲 18 · 774k ↓

16-bit3.1 GB 1 8-bit1.6 GB 0 5-bit1.1 GB 0 4-bit986 MB 4 GGUF~945 MB 0

查看其余 18 个上传项

unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit4-bit 0
lmstudio-community/Qwen2.5-Coder-1.5B-Instruct-GGUFGGUF 0
unsloth/Qwen2.5-Coder-1.5B-bnb-4bit4-bit 0
lmstudio-community/Qwen2.5-Coder-1.5B-Instruct-MLX-8bit8-bit 3
unsloth/Qwen2.5-Coder-1.5B-Instruct-GGUFGGUF 0
alphaduriendur/Qwen2.5-Coder-1.5B-Instruct-Q4_K_M-GGUFQ4_K_M 0
lmstudio-community/Qwen2.5-Coder-1.5B-Instruct-MLX-4bit4-bit 5
ggml-org/Qwen2.5-Coder-1.5B-Instruct-Q8_0-GGUFQ8_0 2
ajayk007/Qwen2.5-Coder-1.5B-ShellsmithGGUF 0
Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQAWQ 0
maylore-ai/Temper-1-1.5BFull 0
litert-community/Qwen2.5-Coder-1.5B-Instruct 1
显示 12 / 18 个

Coder 7B34 个上传 · 🧲 20 · 3.6M ↓

16-bit15 GB 1 5-bit5.4 GB 4-bit~3.7 GB 1 GGUF~4.4 GB 4

查看其余 30 个上传项

Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4INT4 1
mlx-community/Qwen2.5-Coder-7B-Instruct-4bit4-bit 1
unsloth/Qwen2.5-Coder-7B-InstructFull 0
bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUFGGUF 0
unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit4-bit 0
lmstudio-community/Qwen2.5-Coder-7B-Instruct-MLX-4bit4-bit 0
BlossomsAI/Qwen2.5-Coder-7B-Instruct-Uncensored-GGUFGGUF 1
unsloth/Qwen2.5-Coder-7B-Instruct-GGUFGGUF 0
Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQAWQ 1
Snowflake/Arctic-Text2SQL-R1-7BFull 0
unsloth/Qwen2.5-Coder-7B-bnb-4bit4-bit 0
Kondara/Qwen2.5-Coder-7B-Instruct-Q4_K_M-GGUFQ4_K_M 0
显示 12 / 30 个

Coder 14B16 个上传 · 🧲 10 · 2.6M ↓

16-bit30 GB 2 4-bit10.0 GB 1 GGUF~8.8 GB 0

查看其余 13 个上传项

Coder 32B12 个上传 · 🧲 3 · 1.6M ↓

16-bit66 GB 0 4-bit19 GB 1 2-bit12 GB GGUF~20 GB 0

查看其余 8 个上传项

Coder · 社区版本 · 11 个上传

Qwen2.5-Coder 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit3B · 4-bit 0
litert-community/Qwen2.5-Coder-3B-Instruct3B 1
WeiboAI/VibeThinker-3B3B · Full 0
unsloth/Qwen2.5-Coder-3B-bnb-4bit3B · 4-bit 0
ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled3B · GGUF
theprint/VanRossum-Qwen2.5-Coder-3B3B · GGUF
DhruvalLabs/VibeThinker-3B-GGUF3B · GGUF
nisten/q3-reasoner-gguf3B · Q3
Cannae-AI/HERETICODER-2.5-3B-IT3B · Full
nisten/q3-reasoner3B · Q3
beyoru/Kats-3B-exp3B · Full

Math 1.5B5 个上传 · 🧲 3 · 152k ↓

16-bit3.1 GB 4 4-bit1.2 GB GGUF~945 MB

查看其余 2 个上传项

WeiboAI/VibeThinker-1.5BFull 1
unsloth/Qwen2.5-Math-1.5BFull 0

Math 7B1 个上传 · 🧲 1 · 37k ↓

16-bit15 GB 0

VL 7B33 个上传 · 🧲 19 · 8.9M ↓

16-bit17 GB 3 8-bit10 GB 0 4-bit~3.7 GB 1 2-bit~1.8 GB GGUF~4.4 GB 2

查看其余 28 个上传项

huihui-ai/Qwen2.5-VL-7B-Instruct-abliteratedFull 2
mlx-community/olmOCR-2-7B-1025-mlx-8bit8-bit 0
allenai/olmOCR-2-7B-1025-FP8FP8 0
RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-DynamicFP8 0
ggml-org/Qwen2.5-VL-7B-Instruct-GGUFGGUF 1
allenai/olmOCR-2-7B-1025Full 0
mlx-community/Qwen2.5-VL-7B-Instruct-4bit4-bit 1
RedHatAI/Qwen2.5-VL-7B-Instruct-quantized.w8a8INT8 0
unsloth/Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit4-bit 1
xlangai/OpenCUA-7BFull 0
PatataAliena/Qwen2.5-VL-7B-Instruct-Q4_K_M-GGUFQ4_K_M 0
NOVAglow646/Monet-7BFull 0
显示 12 / 28 个

VL 32B4 个上传 · 🧲 2 · 1.1M ↓

16-bit68 GB 6 4-bit21 GB 0 2-bit~8.4 GB

查看其余 1 个上传项

coder3101/Qwen2.5-VL-32B-Instruct-hereticFull

VL · 社区版本 · 10 个上传

Qwen2.5-VL 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

typhoon-ai/typhoon-ocr-3b3B · Full 0
mmp2055/Qwen2.5-VL-3B-uncensored-bughunter-v93B · GGUF 0
RedHatAI/Qwen2.5-VL-3B-Instruct-quantized.w8a83B · INT8 0
OmniSVG/OmniSVG3B 0
wangpan-ustc/AtlasVA3B · Full 0
ggml-org/Qwen2.5-VL-3B-Instruct-GGUF3B · GGUF
numind/NuExtract-2.0-4B3B · Full
Efficient-Large-Model/Fast_dVLM_3B3B · Full
Erland/Qwen2.5-VL-3B-Instruct-bnb-4bit-test3B · 4-bit
RJTPP/th_reasoning-02-qwen2.5-3b_VL-reasoning3B · Full

Qwen

2年前发布1.5B7B9B14B32B35B 90

1.5B34 个上传 · 🧲 10 · 817k ↓

16-bit3.6 GB 1 8-bit1.9 GB 5-bit1.3 GB 4-bit1.1 GB 3-bit861 MB GGUF~945 MB 0

查看其余 28 个上传项

7B19 个上传 · 🧲 10 · 352k ↓

16-bit15 GB 0 4-bit4.7 GB 2 GGUF~4.4 GB 2

查看其余 16 个上传项

9B17 个上传 · 🧲 10 · 48k ↓

16-bit~19 GB 1 4-bit~4.7 GB 0 GGUF~5.7 GB 0

查看其余 14 个上传项

saidutta69/MiMo-V2.6-Distill-Qwen-9B-hereticGGUF 2
Hikari07jp/MiMo-V2.6-Distill-Qwen-9B-AblitratedGGUF 5
ggml-org/MiMo-V2.6-Distill-Qwen-9B-GGUFGGUF 14
mradermacher/MiMo-V2.6-Distill-Qwen-9B-ablit-i1-GGUFGGUF 0
0xSojalSec/Abliterated-MiMo-V2.6-Distill-Qwen-9B-GGUF-MLXGGUF 0
Blackfrost-AI/MiMo-V2.6-Distill-Qwen-9B-Derisked-BF16BF16 1
airun-ai/GlanceRAG-MiMo-9B-RerankerFull 0
base11231/Qwen-Image-2.1-PE-I2I-AbliteratedFull
OliviaRossi/MiMo-Ornith-9B-AGSI-Abliterated-HQFull
webmp3/Sakura-MiMo-V2.6-Distill-Qwen-9B-GGUFGGUF
OliviaRossi/MiMo-Ornith-9B-AGSIFull
mondk/MiMo-V2.6-Distill-Qwen-9B-GGUFGGUF
显示 12 / 14 个

14B18 个上传 · 🧲 4 · 229k ↓

16-bit30 GB 8-bit16 GB 6-bit12 GB 4-bit10.0 GB 0 GGUF~8.8 GB 5

查看其余 13 个上传项

32B50 个上传 · 🧲 7 · 720k ↓

16-bit66 GB 1 8-bit35 GB 4-bit~17 GB 0 GGUF~20 GB 0

查看其余 46 个上传项

35B激活 3B7 个上传 · 🧲 1 · 169k ↓

16-bit~74 GB 8-bit37 GB 4-bit22 GB GGUF~22 GB 6

查看其余 3 个上传项

社区版本 · 15 个上传

Qwen 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-GGUFGGUF 10
optimum-intel-internal-testing/tiny-videochat-flash-qwen10M · Full 1
Xennon-BD/Qwen-Uncensored-ggufGGUF 0
MiniLLM/MiniPLM-Qwen-200M200M · Full 0
NorseDrunkenSailor/Qwen_smol_GH11431M · Full 1
Novaciano/Qwen2.5_Uncensored_V2_Sexting-GGUFGGUF 0
tensorblock/Qwen-uncensored-v2-GGUFGGUF 0
toeniant/Qwen-SEA-LION-v4.5-27B-IT-FP8-Dynamic27B · FP8 2
Ayt1da/qwen-in-qwen-tinyFull 0
csharikrishna/snif-qwen-deepseek17M · Full 0
mradermacher/Qwen-2B-Thai-Reasoning-Opus4.6-Distilled-GGUF2B · GGUF 0
anilsuthar2004/qwen-botGGUF 1
显示 12 / 15 个

Qwen1.5

3年前发布1.8B 7

1.8B3 个上传 · 🧲 2 · 4.6k ↓

16-bit3.7 GB GGUF~1.1 GB 1

社区版本 · 4 个上传

Qwen1.5 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

numind/NuExtract-tiny0.5B · Full 6
ducanhdinh/Qwen1.5-MoE-A2.7B-MidAlign7B · Full 0
sigridjineth/gte-Qwen1.5-7B-instruct-distilled7B · Full 0
fxmarty/qwen_1.5-moe-a2.7b-mxfp47B · MXFP4

Qwen2

3年前发布0.5B1.5B7B57BMath 1.5BMath 7BVL 2BVL 7B 48

0.5B16 个上传 · 🧲 14 · 616k ↓

16-bit1000 MB 2 8-bit~525 MB 0 4-bit~263 MB 0 GGUF~315 MB 0

查看其余 12 个上传项

1.5B10 个上传 · 🧲 8 · 187k ↓

16-bit3.1 GB 3 8-bit1.8 GB 0 4-bit~788 MB 1

查看其余 7 个上传项

Qwen/Qwen2-1.5B-InstructFull 1
DeepMount00/Qwen2-1.5B-ItaFull 0
e-palmisano/Qwen2-1.5B-ITA-InstructFull 0
Qwen/Qwen2-1.5B-Instruct-GPTQ-Int4INT4 2
Qwen/Qwen2-1.5B-Instruct-MLXFull 0
Hack337/WavGPT-1.0Full
Hack337/WavGPT-1.0-mergedFull

7B21 个上传 · 🧲 6 · 496k ↓

16-bit15 GB 0 8-bit8.1 GB 5-bit5.4 GB 4-bit~3.7 GB 0 GGUF~4.4 GB 1

查看其余 16 个上传项

Qwen/Qwen2-7BFull 0
llava-hf/llava-onevision-qwen2-7b-ov-hfFull 0
Qwen/Qwen2-7B-Instruct-MLXFull 0
MCG-NJU/StreamForest-Qwen2-7BFull
augmxnt/Qwen2-7B-Instruct-deccpFull
NikolayKozloff/Qwen2-7B-Instruct-Q4_K_M-GGUFQ4_K_M
tensorblock/Qwen2-7B-Instruct-GGUFGGUF
lmms-lab/EgoGPT-7b-EgoIT-EgoLifeFull
eebyp/Qwen2-7B-Instruct-hqx-2024_01-GGUFGGUF
v8karlo/Qwen2-7B-Q5_K_M-GGUFQ5_K_M
MCG-NJU/StreamForest-Pretrain-Qwen2-7BFull
MCG-NJU/StreamForest-Drive-Qwen2-7BFull
显示 12 / 16 个

57B激活 14B1 个上传 · 🧲 1 · 12k ↓

16-bit115 GB 0

社区版本 · 5 个上传

Qwen2 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

optimum-intel-internal-testing/tiny-dummy-qwen2Full 1
fxmarty/tiny-dummy-qwen2Full 1
pgy520/Qwen2-Boundless-Q4_K_M-GGUFQ4_K_M 1
wencan25/tinystories_qwen225M · Full 1
llava-hf/llava-onevision-qwen2-72b-ov-hf72B · Full

Math 1.5B3 个上传 · 🧲 2 · 5.8k ↓

16-bit3.1 GB 0 GGUF~945 MB

查看其余 1 个上传项

Qwen/Qwen2-Math-1.5B-InstructFull 0

Math 7B2 个上传 · 🧲 2 · 1.9k ↓

16-bit15 GB 0

查看其余 1 个上传项

Qwen/Qwen2-Math-7BFull 0

VL 2B16 个上传 · 🧲 10 · 1.2M ↓

16-bit4.4 GB 1 8-bit~2.1 GB 0 4-bit~1.1 GB 0 GGUF1.5 GB

查看其余 12 个上传项

VL 7B17 个上传 · 🧲 7 · 1.2M ↓

16-bit17 GB 3 8-bit10 GB 0 4-bit~3.7 GB 1

查看其余 14 个上传项

allenai/olmOCR-7B-0225-previewFull 2
Qwen/Qwen2-VL-7BFull 0
CraftJarvis/minecraft-openha-qwen2vl-7b-2509Full 0
microsoft/GUI-Actor-7B-Qwen2-VLFull 0
lmms-lab/Qwen2-VL-2B-GRPO-8kFull
TIGER-Lab/VLM2Vec-Qwen2VL-7B
TIGER-Lab/VLM2Vec-Qwen2VL-2B
adamo1139/Qwen2-VL-7B-SydneyFull
ashimdahal/Ertugrul-Qwen2-VL-7B-Captioner-Relaxed_Qwen-Qwen2-VL-7B-InstructFull
HongxinLi/UIPro-7B_Stage2_MobileFull
HongxinLi/UIPro-7B_Stage1Full
HongxinLi/UIPro-7B_Stage2_WebFull
显示 12 / 14 个

qwen0.5b

5B 0

5B1 个上传 · 🧲 1 · 31 ↓

GGUF~3.1 GB 0

Qwen25

7B15B 0

7B1 个上传 · 8 ↓

16-bit~15 GB

15B1 个上传 · 7 ↓

16-bit~32 GB

qwen27b

28B 0

28B1 个上传 · 33 ↓

4-bit18 GB

Qwen3.9

245B 0

245B激活 29B1 个上传 · 91 ↓

16-bit~515 GB

qwen35

27B 0

27B3 个上传 · 132 ↓

16-bit~57 GB

查看其余 2 个上传项

qwen38

27B 0

大小未知1 个上传 · 272 ↓

GGUF

27B1 个上传 · 32 ↓

16-bit56 GB

qwen3loop

0.6B 0

0.6B1 个上传 · 🧲 1 · 742 ↓

GGUF~378 MB 0

qwen4b

2

大小未知3 个上传 · 🧲 2 · 446k ↓

16-bit 1

查看其余 2 个上传项

chewwt/hpo_qwen4b_emulatorFull 1
chewwt/dm_qwen4b_noise_emulatorFull

qwen72b

v0.8 72B 0

v0.8 72B1 个上传 · 🧲 1 · 9.0k ↓

16-bit145 GB 0

qwen8b

1

大小未知1 个上传 · 🧲 1 · 353k ↓

16-bit 1

QwenCoder

14B7B 2

14B1 个上传 · 🧲 1 · 1.3k ↓

GGUF~8.8 GB 2

7B1 个上传 · 16 ↓

16-bit15 GB

QwenPaw-Flash

9B 0

9B2 个上传 · 482 ↓

4-bit5.6 GB GGUF~5.7 GB

Qwenseek-3.8

27B 0

27B1 个上传 · 🧲 1 · 2.7k ↓

GGUF~17 GB 0

Qwenstral-Small-3.1

0.5B 1

0.5B1 个上传 · 🧲 1 · 2.3k ↓

16-bit1.2 GB 1

模型 669k+

浏览模型

Qwen3.8

Qwen3.6

Qwen3.5

Qwen3

QwQ

Qwen2.5

Qwen

Qwen1.5

Qwen2

qwen0.5b

Qwen25

qwen27b

Qwen3.9

qwen35

qwen38

qwen3loop

qwen4b

qwen72b

qwen8b

QwenCoder

QwenPaw-Flash

Qwenseek-3.8

Qwenstral-Small-3.1