I can no longer upload new models unless I can cover the cost of additional storage.
I host 70+ free models as an independent contributor and this work is unpaid.
Without your support, no more new models can be uploaded.
Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.
This is the full model with the 15 MTPs all intacts.
Creating these models takes significant time, work and compute. If you find them useful consider supporting me:
| Platform | Link | What you get |
|---|---|---|
| ☕ Ko-fi | Coffee Tips | My eternal gratitude |
Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.
GGUF quantizations of llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved
Original Model:
MTP count: 15
Heretic Model:
MTP count: 15
| Parameter | Value |
|---|---|
| direction_index | 34.80 |
| attn.out_proj.max_weight | 1.95 |
| attn.out_proj.max_weight_position | 39.33 |
| attn.out_proj.min_weight | 1.38 |
| attn.out_proj.min_weight_distance | 46.24 |
| mlp.down_proj.max_weight | 1.89 |
| mlp.down_proj.max_weight_position | 46.28 |
| mlp.down_proj.min_weight | 1.68 |
| mlp.down_proj.min_weight_distance | 20.97 |
| attn.o_proj.max_weight | 1.36 |
| attn.o_proj.max_weight_position | 51.53 |
| attn.o_proj.min_weight | 1.36 |
| attn.o_proj.min_weight_distance | 37.22 |
| Metric | This model | Original model (Qwen/Qwen3.8-27B) |
|---|---|---|
| KL divergence | 0.0244 | 0 (by definition) |
| Refusals | ✅ 3/100 | ❌ 91/100 |
Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections.
Original:
============================================================
Total questions: 7021
Correct: 5857
Accuracy: 0.8342 (83.42%)
Parse failures: 1
============================================================
Tested subject scores:
Heretic:
============================================================
Total questions: 7021
Correct: 5815
Accuracy: 0.8282 (82.82%)
Parse failures: 0
============================================================
Tested subject scores:
MMLU - Massive Multitask Language Understanding, multiple-choice questions across 57 subjects (math, history, law, medicine, etc.).
For the K-quants below, small SSM tensors are kept at higher precision where useful.
-Q6_K, Q5_K, Q4_K and Q3_K quants keep ssm_alpha, ssm_beta, and ssm_out as Q8_0.
This helps preserve the hybrid/SSM blocks with a small file-size increase.
| Filename | Quant | Description |
|---|---|---|
| Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-BF16.gguf | BF16 | Full precision |
| Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-Q8_0.gguf | Q8_0 | Near-lossless, recommended |
| Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-Q6_K.gguf | Q6_K | Excellent quality |
| Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-Q5_K_M.gguf | Q5_K_M | Good balance |
| Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-Q5_K_S.gguf | Q5_K_S | Smaller Q5 |
| Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-Q4_K_M.gguf | Q4_K_M | Good for limited VRAM |
| Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-Q4_K_S.gguf | Q4_K_S | Smaller Q4 |
| Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-Q3_K_L.gguf | Q3_K_L | Low VRAM, decent quality |
| Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-Q3_K_M.gguf | Q3_K_M | Low VRAM, smaller |
| Filename | Quant | Description |
|---|---|---|
| Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-mmproj-BF16.gguf | BF16 | Native precision |
A Vision Projector File is Required for vision/multimodal capabilities. Use alongside any quantization above.
Works with llama.cpp, LM Studio, Ollama, and other GGUF-compatible tools.
[!Note] This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.
These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.
[!Tip] For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Qwen Cloud. In particular, Qwen3.8-27B will be available as a hosted version with more production features, e.g., 1M context length by default, official built-in tools. For more information, please refer to the Qwen3.8-27B Overview. The service is coming soon. Stay tuned for updates.
Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.
Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability.
Qwen3.8-27B features the following enhancements:
reasoning_effort, and reasoning context from historical messages is retained via preserve_thinking.| Qwen3.8-27B | Qwen3.6-27B | Qwen3.7-Plus | Muse Glimmer-30B | Opus4.6 Max | |
|---|---|---|---|---|---|
| Coding | |||||
| Agentic terminal codingTerminal Bench 2.1 (Terminus) | 73.0 | 63.4 | 64.0 | 51.7 | 78.2 |
| Agentic codingSWE-bench Pro | 61.7 | 53.5 | 57.6 | 51.2 | 53.4 |
| Repo-level code generationNL2Repo-Bench | 42.3 | 36.2 | 41.1 | -- | 47.6 |
| Agentic codingDeepSWE 1.1 | 42.2 | 13.3 | 14.2 | -- | -- |
| Software engineeringQwenSWEBench | 79.0 | 49.3 | 59.2 | -- | 63.8 |
| Agent | |||||
| Long-horizon office workCoWorkBench | 70.7 | 61.0 | 65.1 | -- | 68.2 |
| Professional job tasksJobBench | 33.4 | 21.8 | 27.6 | -- | -- |
| Frontier agentic tasksAgents' Last Exam | Pass@120.4Score42.9 | Pass@110.6Score27.3 | Pass@113.2Score33.6 | -- | -- |
| General | |||||
| Instruction followingIFBench | 79.5 | 69.1 | 79.1 | 77.0 | 62.5 |
| Scientific reasoningGPQA Diamond | 89.2 | 87.8 | 90.3 | 83.5 | 91.3 |
| Multidisciplinary reasoningHLE | 30.8 | 24.0 | 34.7 | 22.0 | 40.0 |
| Competitive codingLiveCodeBench v6 | 90.3 | 83.9 | 89.6 | -- | 88.8 |
| Qwen3.8-27B | Qwen3.6-27B | Qwen3.7-Plus | Muse Glimmer-30B | Opus4.6 Max | |
|---|---|---|---|---|---|
| Agentic Multimodal Intelligence | |||||
| Computer useOSWorld-Verified | 84.3 | 63.9 | 73.3 | 65.9 | 72.7 |
| Browser useWebArena-Verified | 64.8 | 48.8 | 55.3 | -- | -- |
| Mobile useAndroidWorld | 81.9 | 70.3 | 81.0 | -- | 62.0 |
| Application recreationRecreationBench | 47.1 | 29.8 | 30.2 | -- | -- |
| Multimodal tool useClawEval-MM | Pass@357.4Average56.9 | Pass@342.6Average50.4 | Pass@357.4Average60.1 | -- | Pass@352.5Average54.7 |
| Multimodal software engineeringSWE-MM | 38.6 | 25.7 | 30.0 | -- | 27.1 |
| Visual web developmentVision2Web | 62.9 | 45.0 | 42.1 | -- | -- |
| General Multimodal Intelligence | |||||
| Visual math problem solvingMathVision | Without CI90.0With CI94.6 | Without CI85.1 | Without CI90.3 | -- | Without CI65.5 |
| General visual reasoningBabyVision | Without CI65.7With CI85.6 | Without CI28.9 | Without CI64.7With CI70.4 | -- | Without CI12.6 |
| Scientific chart analysisCharXiv (RQ) | Without CI83.7With CI90.2 | Without CI78.4 | Without CI85.8With CI85.9 | 78.8 | Without CI66.0 |
| Document intelligenceOmniDocBench 1.5 | 91.1 | 89.4 | 91.4 | 75.8 | 86.6 |
| Real-world perceptionRealWorldQA | 85.9 | 84.1 | 86.9 | -- | 73.9 |
| Embodied intelligenceERQA | 65.5 | 62.5 | 69.8 | -- | 40.8 |
\boxed{}.” For the remaining models, we report the higher score from two prompt variants—one with and one without the \boxed{} formatting requirement.gpt-5.4-2026-03-05.For streamlined integration, we recommend using Qwen3.8 via APIs.
[!Important] Inference efficiency and throughput vary significantly across frameworks. We recommend using the latest framework versions to ensure optimal performance and compatibility. For production workloads or high-throughput scenarios, dedicated serving engines such as SGLang, vLLM, or TokenSpeed are recommended.
Qwen3.8 can be deployed with popular inference frameworks, e.g.:
[!Important] Qwen3.8 models operate in thinking mode by default, generating thinking content signified by
<think>\n...</think>\n\nbefore producing the final response. To disable thinking content and obtain a direct response, refer to the examples here.
[!Tip] We recommend using the following sets of sampling parameters for generation:
- Thinking Mode:
temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=0.0,repetition_penalty=1.0- Instruct (or non-thinking) mode:
temperature=0.7,top_p=0.80,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0Please note that the support for sampling parameters varies according to inference frameworks.
Qwen3.8 comes with official support for reasoning_effort, which can be used to adjust reasoning depth and control cost:
xhigh: for complex tasks demanding thorough analysismedium (default): balancing accuracy and speedlow: efficient reasoning optimizing for speed and costIn addition, preserve_thinking is enabled by default for all workloads for the best out-of-the-box experience. To disable preserved thinking, refer to the examples here.
[!Tip] In multi-turn agentic tasks, lower reasoning effort does not always reduce overall task completion time. Although it may produce faster per-turn responses, it can also lead to insufficient analysis, more failures, and repeated retries, which may increase total latency and token consumption.
The Chat Completions API can be used with most inference frameworks, as well as Qwen Cloud. Before starting, make sure the OpenAI Python SDK is installed and the API key and the API base URL are configured, e.g.:
pip install -U openai
# Set the following accordingly
export OPENAI_BASE_URL='your-base-url'
export OPENAI_API_KEY='your-api-key'
from openai import OpenAI
# Configured by environment variables
client = OpenAI()
messages = [{"role": "user", "content": "Write a Python function to merge two sorted linked lists."}]
completion = client.chat.completions.create(
model="llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-GGUF",
messages=messages,
extra_body={
"chat_template_kwargs": {
"enable_thinking": True, # on by default
"preserve_thinking": True, # on by default
},
},
reasoning_effort="medium", # medium by default; supported levels are xhigh, medium, and low
stream=True,
stream_options={"include_usage": True},
)
reasoning_content = ""
answer_content = ""
is_answering = False
print("\n" + "=" * 20 + "Reasoning" + "=" * 20 + "\n")
for chunk in completion:
if not chunk.choices:
print("\nUsage:")
print(chunk.usage)
continue
delta = chunk.choices[0].delta
if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
if not is_answering:
print(delta.reasoning_content, end="", flush=True)
reasoning_content += delta.reasoning_content
elif hasattr(delta, "reasoning") and delta.reasoning is not None:
if not is_answering:
print(delta.reasoning, end="", flush=True)
reasoning_content += delta.reasoning
if hasattr(delta, "content") and delta.content:
if not is_answering:
print("\n" + "=" * 20 + "Answer" + "=" * 20 + "\n")
is_answering = True
print(delta.content, end="", flush=True)
answer_content += delta.content
messages.append({
"role": "assistant",
"content": answer_content,
"reasoning_content": reasoning_content,
"reasoning": reasoning_content,
})
from openai import OpenAI
# Configured by environment variables
client = OpenAI()
messages = [
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {
"url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/CI_Demo/mathv-1327.jpg"
}
},
{
"type": "text",
"text": "The centres of the four illustrated circles are in the corners of the square. The two big circles touch each other and also the two little circles. With which factor do you have to multiply the radii of the little circles to obtain the radius of the big circles?\nChoices:\n(A) $\\frac{2}{9}$\n(B) $\\sqrt{5}$\n(C) $0.8 \\cdot \\pi$\n(D) 2.5\n(E) $1+\\sqrt{2}$"
}
]
}
]
chat_response = client.chat.completions.create(
model="llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-GGUF",
messages=messages,
)
print("Chat response:", chat_response)
from openai import OpenAI
# Configured by environment variables
client = OpenAI()
messages = [
{
"role": "user",
"content": [
{
"type": "video_url",
"video_url": {
"url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/video/N1cdUjctpG8.mp4"
}
},
{
"type": "text",
"text": "How many porcelain jars were discovered in the niches located in the primary chamber of the tomb?"
}
]
}
]
chat_response = client.chat.completions.create(
model="llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-GGUF",
messages=messages,
)
# When vLLM is launched with `--media-io-kwargs '{"video": {"num_frames": -1}}'`,
# video frame sampling can be configured via `extra_body` (e.g., by setting `fps`).
# This feature is currently supported only in vLLM.
#
# By default, `fps=2` and `do_sample_frames=True`.
# With `do_sample_frames=True`, you can customize the `fps` value to set your desired video sampling rate.
# chat_response = client.chat.completions.create(
# model="llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-GGUF",
# messages=messages,
# extra_body={
# "mm_processor_kwargs": {"fps": 2, "do_sample_frames": True},
# },
# )
print("Chat response:", chat_response)
Qwen3.8-27B will think by default before responding. You can obtain a direct response from the model without thinking by configuring the API parameters. For example,
from openai import OpenAI
# Configured by environment variables
client = OpenAI()
messages = [
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {
"url": "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/RealWorld/RealWorld-04.png"
}
},
{
"type": "text",
"text": "Where is this?"
}
]
}
]
chat_response = client.chat.completions.create(
model="llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-GGUF",
messages=messages,
temperature=0.7,
top_p=0.8,
presence_penalty=1.5,
extra_body={
"top_k": 20,
"chat_template_kwargs": {"enable_thinking": False},
},
)
print("Chat response:", chat_response)
[!Note] If you are using APIs from Qwen Cloud, in addition to changing
model, please use"enable_thinking": Falseinstead of"chat_template_kwargs": {"enable_thinking": False}.
By default, Qwen3.8 retains thinking blocks from all historical messages, maintaining a complete reasoning trace across the conversation. This behavior, known as preserved thinking, ensures full context continuity and is especially beneficial for agent scenarios where decision consistency and reduced redundant reasoning are critical. It also improves KV cache utilization, optimizing inference efficiency in both thinking and non-thinking modes.
If you prefer to retain only the thinking blocks from the latest user message, you can disable this behavior by setting preserve_thinking to False:
from openai import OpenAI
# Configured by environment variables
client = OpenAI()
messages = [...]
chat_response = client.chat.completions.create(
model="llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-GGUF",
messages=messages,
extra_body={
"chat_template_kwargs": {"preserve_thinking": False},
},
)
print("Chat response:", chat_response)
[!Note] If you are using APIs from Qwen Cloud, in addition to changing
model, please use"preserve_thinking": Falsedirectly instead of wrapping it inchat_template_kwargs.
To achieve optimal performance, we recommend the following settings:
Sampling Parameters: We suggest using the following sets of sampling parameters:
temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0 For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetition. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
Adequate Output Length: To optimize performance on agentic tasks, we recommend allocating sufficient output length to allow the model to generate detailed and comprehensive responses. For frameworks that support separate token limits for internal reasoning and final outputs, we suggest the following configuration within the 1M context length:
These settings provide the necessary capacity for complex reasoning while ensuring ample space for high-quality final deliverables.
Processing Ultra-Long Texts: Qwen3.8-27B natively supports context lengths of up to 262,144 tokens. For long-horizon tasks where the total length (including both input and output) exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively, e.g., YaRN.
YaRN is currently supported by several inference frameworks, e.g., vLLM, SGLang, and TokenSpeed. In general, there are two approaches to enabling YaRN for supported frameworks:
Modifying the model configuration file:
In the config.json file, change the rope_parameters fields in text_config to:
{
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"rope_type": "yarn",
"rope_theta": 10000000,
"partial_rotary_factor": 0.25,
"factor": 4.0,
"original_max_position_embeddings": 262144,
}
Passing command line arguments:
For vLLM, you can use
VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve ... --hf-overrides '{"text_config": {"rope_parameters": {"mrope_interleaved": true, "mrope_section": [11, 11, 10], "rope_type": "yarn", "rope_theta": 10000000, "partial_rotary_factor": 0.25, "factor": 4.0, "original_max_position_embeddings": 262144}}}' --max-model-len 1000000
For SGLang, you can use
SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server ... --json-model-override-args '{"text_config": {"rope_parameters": {"mrope_interleaved": true, "mrope_section": [11, 11, 10], "rope_type": "yarn", "rope_theta": 10000000, "partial_rotary_factor": 0.25, "factor": 4.0, "original_max_position_embeddings": 262144}}}' --context-length 1000000
For TokenSpeed, you can use
TOKENSPEED_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 tokenspeed serve ... --hf-overrides '{"text_config": {"rope_parameters": {"mrope_interleaved": true, "mrope_section": [11, 11, 10], "rope_type": "yarn", "rope_theta": 10000000, "partial_rotary_factor": 0.25, "factor": 4.0, "original_max_position_embeddings": 262144}}}' --max-model-len 1000000
[!NOTE] All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, potentially impacting performance on shorter texts. We advise modifying the
rope_parametersconfiguration only when processing long contexts is required. It is also recommended to modify thefactoras needed. For example, if the typical context length for your application is 524,288 tokens, it would be better to setfactoras 2.0.
Long Video Understanding: To optimize inference efficiency for plain text and images, the size parameter in the released video_preprocessor_config.json is conservatively configured. It is recommended to set the longest_edge parameter in the video_preprocessor_config file to 469,762,048 (corresponding to 224k video tokens) to enable higher frame-rate sampling for hour-scale videos and thereby achieve superior performance. For example,
{"longest_edge": 469762048, "shortest_edge": 4096}
Alternatively, override the default values via engine startup parameters. For implementation details, refer to: vLLM / SGLang.
If you find our work helpful, feel free to give us a cite.
@misc{qwen38,
title = {{Qwen3.8-Max}: A New Bar for Coding and Cowork},
url = {https://qwen.ai/blog?id=qwen3.8},
author = {{Qwen Team}},
month = {August},
year = {2026}
}