模型 · Pirate Face

gemma-4

7个月前发布2B4B12B26B31B 528

2B69 个上传 · 🧲 47 · 7.0M ↓

16-bit~4.2 GB 4 8-bit~2.1 GB 1 6-bit~1.6 GB 1 5-bit~1.3 GB 1 4-bit~1.1 GB 1 2-bit~525 MB GGUF~1.3 GB 1

查看其余 62 个上传项

unsloth/gemma-4-E2B-it-qat-mobile-GGUFGGUF 0
turintech/gemma-4-E2B-it-Artemis-GGUFGGUF 0
lmstudio-community/gemma-4-E2B-it-MLX-4bit4-bit 1
google/gemma-4-E2B-it-qat-q4_0-ggufQ4_0 6
lmstudio-community/gemma-4-E2B-it-GGUFGGUF 3
google/gemma-4-E2BFull 0
HauhauCS/Gemma-4-E2B-Uncensored-HauhauCS-AggressiveGGUF 0
unsloth/gemma-4-E2B-it-unsloth-bnb-4bit4-bit 0
unsloth/gemma-4-E2B-it-qat-GGUFGGUF 1
bartowski/google_gemma-4-E2B-it-GGUFGGUF 1
unsloth/gemma-4-E2B-itFull 0
google/gemma-4-E2B-it-assistantFull 5
显示 12 / 62 个

4B155 个上传 · 🧲 113 · 14M ↓

16-bit~8.4 GB 3 8-bit~4.2 GB 1 6-bit~3.1 GB 1 5-bit~2.6 GB 1 4-bit~2.1 GB 1 3-bit~1.6 GB 0 2-bit~1.1 GB 0 GGUF~2.5 GB 1

查看其余 147 个上传项

lmstudio-community/gemma-4-E4B-it-MLX-4bit4-bit 1
HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-AggressiveGGUF 0
lmstudio-community/gemma-4-E4B-it-GGUFGGUF 1
google/gemma-4-E4BFull 2
ggml-org/gemma-4-E4B-it-GGUFGGUF 8
google/gemma-4-E4B-it-qat-w4a16-ctINT4 1
llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUFGGUF 2
unsloth/gemma-4-E4B-it-qat-GGUFGGUF 3
unsloth/gemma-4-E4B-it-unsloth-bnb-4bit4-bit 0
OBLITERATUS/gemma-4-E4B-it-OBLITERATEDGGUF 4
unsloth/gemma-4-E4B-it-qat-mobile-GGUFGGUF 1
OpenVINO/gemma-4-E4B-it-int8-ovINT8 0
显示 12 / 147 个

12B84 个上传 · 🧲 55 · 10M ↓

16-bit24 GB 2 8-bit13 GB 0 6-bit9.8 GB 1 5-bit8.3 GB 1 4-bit7.2 GB 1 2-bit~3.1 GB 2 GGUF~7.6 GB 1

查看其余 77 个上传项

HauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-BalancedGGUF 1
google/gemma-4-12B-it-qat-w4a16-ctINT4 3
jialinyyzz/humanizerGGUF 1
lmstudio-community/gemma-4-12B-it-MLX-4bit4-bit 1
lmstudio-community/gemma-4-12B-it-QAT-GGUFGGUF 0
unsloth/gemma-4-12B-it-qat-GGUFGGUF 3
lmstudio-community/gemma-4-12B-it-GGUFGGUF 1
ggml-org/gemma-4-12B-it-GGUFGGUF 0
yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUFGGUF 3
culturerevolt/gemma-4-12b-heretic-abliterated-GGUFGGUF 2
cyankiwi/gemma-4-12B-it-AWQ-INT4INT4 0
google/gemma-4-12BFull 3
显示 12 / 77 个

26B激活 4B93 个上传 · 🧲 53 · 19M ↓

16-bit52 GB 8 8-bit29 GB 1 6-bit~20 GB 0 5-bit~17 GB 0 4-bit19 GB 1 2-bit~6.8 GB GGUF~16 GB 3

查看其余 86 个上传项

cyankiwi/gemma-4-26B-A4B-it-AWQ-4bitAWQ 1
RedHatAI/gemma-4-26B-A4B-it-NVFP4NVFP4 0
HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTPGGUF 2
google/gemma-4-26B-A4B-it-assistantFull 1
lmstudio-community/gemma-4-26B-A4B-it-QAT-MLX-4bit4-bit 0
ggml-org/gemma-4-26B-A4B-it-GGUFGGUF 1
FINAL-Bench/POCKET-26B-GGUFGGUF 0
google/gemma-4-26B-A4B-it-qat-q4_0-ggufQ4_0 0
unsloth/gemma-4-26B-A4B-it-qat-GGUFGGUF 3
lmstudio-community/gemma-4-26B-A4B-it-MLX-4bit4-bit 0
lmstudio-community/gemma-4-26B-A4B-it-MLX-8bit8-bit 0
lmstudio-community/gemma-4-26B-A4B-it-QAT-GGUFGGUF 0
显示 12 / 86 个

31B101 个上传 · 🧲 49 · 12M ↓

16-bit63 GB 6 Other~65 GB 8-bit33 GB 6 6-bit26 GB 0 5-bit22 GB 0 4-bit20 GB 0 2-bit~8.1 GB GGUF~20 GB 0

查看其余 93 个上传项

cyankiwi/gemma-4-31B-it-AWQ-4bitAWQ 0
google/gemma-4-31B-it-qat-w4a16-ctINT4 0
google/gemma-4-31B-it-assistantFull 2
lmstudio-community/gemma-4-31B-it-MLX-8bit8-bit 0
lmstudio-community/gemma-4-31B-it-MLX-4bit4-bit 0
google/gemma-4-31B-it-qat-q4_0-ggufQ4_0 0
RedHatAI/gemma-4-31B-it-FP8-dynamicFP8 0
unsloth/gemma-4-31B-it-qat-GGUFGGUF 0
lmstudio-community/gemma-4-31B-it-QAT-GGUFGGUF 0
HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTPGGUF 0
llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-GGUFGGUF 2
llmfan46/gemma-4-31B-it-uncensored-heretic-GGUFGGUF 4
显示 12 / 93 个

社区版本 · 14 个上传

gemma-4 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-gemma4-moeFull 0
optimum-intel-internal-testing/tiny-random-gemma4-unifiedFull 0
optimum-intel-internal-testing/tiny-random-gemma412M · Full 0
optimum-intel-internal-testing/tiny-random-gemma4-unified-itFull 0
AlexKoff88/gemma4_tinystories38M · Full 0
mradermacher/gemma-4-19B-A4B-it-The-DECKARD-Heretic-Uncensored-Thinking-i1-GGUF19B · GGUF 0
optimum-intel-internal-testing/tiny-random-gemma4-dflashFull 1
deadbydawn101/gemma-4-21b-REAP-Tool-Calling-mlx-4bit21B · 4-bit
LLMWildling/gemma-4-70b-a7b-coder70B · Full
JThomas-CoE/coe-gemma4-psychology-mmlu_pro-14b-a4b-q414B · Q4
LLMWildling/gemma-4-80b-a8b-coder80B · Full
LLMWildling/gemma-4-90b-a9b-coder90B · Full
显示 12 / 14 个

gemma-3

2年前发布270M1B4B12B 27

270M13 个上传 · 🧲 4 · 121k ↓

16-bit575 MB 9 8-bit292 MB 4-bit~142 MB

查看其余 9 个上传项

1B24 个上传 · 🧲 6 · 684k ↓

16-bit2.0 GB 0 8-bit1.1 GB GGUF~630 MB 0

查看其余 20 个上传项

bartowski/huihui-ai_gemma-3-1b-it-abliterated-GGUFGGUF 0
scratchyone/anon-1bGGUF 0
CALISTA-INDUSTRY/gemma_3_4B_reasoning_multimodal_en_ft_v2GGUF 0
distil-labs/distil-ai-slop-detector-gemmaFull 2
ggml-org/gemma-3-1b-it-GGUFGGUF
Andycurrent/Gemma-3-1B-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking_GGUFGGUF
litert-community/Gemma3-1B-IT
tardellirs/aac-board-generator-770m-ptbrFull
farbodtavakkoli/OTel-LLM-1B-ITFull
KittyLM/kittylm-gemma3-1b-ggufGGUF
KittyLM/kittylm-gemma3-1bFull
ZeroWw/gemma-3-1b-it-GGUFGGUF
显示 12 / 20 个

4B24 个上传 · 🧲 1 · 1.3M ↓

16-bit8.6 GB 8-bit4.1 GB 4-bit~2.1 GB GGUF~2.5 GB 16

查看其余 20 个上传项

12B17 个上传 · 🧲 2 · 391k ↓

16-bit24 GB 0 6-bit9.7 GB 5-bit8.4 GB 4-bit8.1 GB GGUF5.2 GB 0

查看其余 11 个上传项

社区版本 · 13 个上传

gemma-3 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

QCRI/Fanar-2-27B-Instruct27B · Full 0
farbodtavakkoli/OTel-LLM-27B-IT27B 0
GoToCompany/gemma3-27b-cpt-gotoai-v3-instruct27B · Full 0
gaunernst/gemma-3-27b-it-int4-awq27B · INT4
ISTA-DASLab/gemma-3-27b-it-GPTQ-4b-128g27B · GPTQ
Thaurock/Gemma-3-27b-it-abliterated-GGUF27B · GGUF
McG-221/gemma-3-27b-it-abliterated-refined-vision-mlx-8Bit27B · 8-bit
nectec/thai-research-gemma-3-27b-it27B · GGUF
Lucy-in-the-Sky/gemma-3-27b-it-abliterated-Q4_K_M-GGUF27B · Q4_K_M
Justbackup/Gemma-3-27b-it-Uncensored-HERETIC-Gemini-Deep-Reasoning27B · Full
pankajmathur/Mimma-3-27b27B · Full
Luigi/gemma-3-270m-it-dinercall-ner27B · Full
显示 12 / 13 个

gemma-2

2年前发布2B9B 0

2B9 个上传 · 🧲 1 · 112k ↓

16-bit~4.2 GB 8-bit2.8 GB GGUF~1.3 GB 0

查看其余 6 个上传项

9B23 个上传 · 854k ↓

16-bit~19 GB 8-bit9.8 GB 4-bit6.2 GB GGUF~5.7 GB

查看其余 19 个上传项

mlx-community/gemma-2-9b-it-4bit4-bit
ATH-MaaS/Ovis1.6-Gemma2-9BFull
anakin87/gemma-2-9b-neogenesis-itaFull
theprint/CleverBoi-Gemma-2-9BGGUF
theprint/Hemispheres-v0.2-Gemma2-9B-ComboGGUF
theprint/ReWiz-Gemma2-9BGGUF
l3utterfly/Gemma-2-Ataraxy-9B-ggufGGUF
aisingapore/Gemma-SEA-LION-v3-9BFull
NikolayKozloff/Gemma-2-9B-It-SPPO-Iter3-IQ4_XS-GGUFIQ4_XS
agentlans/Gemma2-9B-AdvancedFuseFull
grimjim/Magnolia-v2-Gemma2-8k-9BFull
NikolayKozloff/Gemma-2-9B-It-SPPO-Iter3-Q4_0-GGUFQ4_0
显示 12 / 19 个

社区版本 · 3 个上传

gemma-2 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

migtissera/Tess-v2.5-Gemma-2-27B-alpha27B
Solstice-AI/C2S-Scale-Gemma-2-27B-Q8_0-GGUF27B · Q8_0
paultimothymooney/gemma-2-27b-it-Q8_0-GGUF27B · Q8_0

gemma

3年前发布2B4B7B 0

2B6 个上传 · 🧲 3 · 106k ↓

16-bit5.0 GB 0 GGUF~1.3 GB

查看其余 4 个上传项

FinancialSupport/hellfire-2bFull 0
Baidicoot/reward_modelingFull 0
NikolayKozloff/gemma-portuguese-luana-2b-GGUFGGUF
deepvk/llava-gemma-2b-loraFull

4B3 个上传 · 1.6k ↓

16-bit9.2 GB 4-bit~2.1 GB

查看其余 1 个上传项

pranjal-pravesh/gemma-3n-E3BFull

7B5 个上传 · 201k ↓

16-bit17 GB GGUF~4.4 GB

查看其余 3 个上传项

社区版本 · 6 个上传

gemma 官方未发布的大小：以它命名的蒸馏、合并等社区模型。

DavidAU/Gemma-The-Writer-N-Restless-Quill-10B-Uncensored-GGUF10B · GGUF
DavidAU/Gemma-The-Writer-Mighty-Sword-9B-GGUF9B · GGUF
Hack337/news-gemma-3n-Q4_K_M-GGUFQ4_K_M
Mollel/Swahili_Gemma
fxmarty/tiny-gemma-onnx-quantized-trt
Hack337/news-gemma-3n8.4B · Full

gemma3n

18M 0

18M1 个上传 · 🧲 1 · 34k ↓

16-bit~38 MB 0

gemma4swift

26B 0

26B激活 4B1 个上传 · 156 ↓

8-bit28 GB

GemmaForCausalLM

2

大小未知2 个上传 · 🧲 2 · 15k ↓

16-bit 1

查看其余 1 个上传项

optimum-intel-internal-testing/tiny-random-GemmaForCausalLMFull 1

Gemmasutra-Mini

2B 0

2B1 个上传 · 69 ↓

GGUF~1.3 GB

模型 669k+

浏览模型