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.
HuatuoGPT-3-27B
FreedomIntelligence·Instruct·released 24 Sept 2026
ollama run hf.co/mradermacher/HuatuoGPT-3-27B-i1-GGUF:Q4_K_MHuatuoGPT-3-27B is a medical LLM built on Qwen3.8-27B with One-stage Policy Optimization (OnePO). OnePO adapts language models to medicine in a single reinforcement-learning stage, without preceding domain-specific supervised fine-tuning.
How much VRAM does HuatuoGPT-3-27B need?
At Q4_K_M HuatuoGPT-3-27B needs about 19 GB with an 8K context (19 GB at Q4, 55 GB at full precision). Pick your GPU to see what fits and how fast it runs.
Needs: ≈19 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.
Advanced: context 8K · KV cache 16-bit
Smallest GPU for each quant and context (KV cache 16-bit)
| Quantisation | 8K | 16K | 32K | 64K | 128K | 256K |
|---|---|---|---|---|---|---|
| Q3_K_M | ||||||
| Q4_K_M | ||||||
| Q5_K_M | ||||||
| Q6_K | ||||||
| Q8_0 | ||||||
| FP16 |
≤16 GB card24–32 GB48–96 GBmore
| Quantisation | Total |
|---|---|
| Q2_KHeavy lossSmallest, noticeably worse quality | ≈13 GB |
| Q3_K_MNoticeable lossSmall, some quality loss | ≈16 GB |
| Q4_K_MrecommendedSmall lossRecommended default for local use | ≈19 GB |
| Q5_K_MNear-losslessNear-lossless for most tasks | ≈21 GB |
| Q6_KNear-losslessPractically lossless | ≈24 GB |
| Q8_0LosslessLossless in practice, twice the size of Q4 | ≈31 GB |
| FP16 / BF16LosslessFull precision, as released | ≈55 GB |
Estimates for 8K tokens of context: weights + KV cache + runtime overhead. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.
How to pick a quant
Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.
- LosslessF16, Q8_0
- Near-losslessQ6_K, Q5_K_M
- Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
- Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
- Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K
Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B
How much context fits?
At 8K context, Q4_K_M needs ≈19 GB(15 GB weights + 2.0 GB KV cache + 1.3 GB overhead). Pick a GPU above to see how much context fits.
Weights + overheadKV cache
Can the Tesla P40 run HuatuoGPT-3-27B? →
Speed vs quality per quant
Smaller quants run faster and fit in less memory, but lose quality.
Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.
Real-world speed of HuatuoGPT-3-27B
Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →
No medians yet. Be one of the first 3 to report a setup.
All reports
Run HuatuoGPT-3-27B locally
--quantQ4_K_Mdefault; pick your GPU to tailor itmradermacher/HuatuoGPT-3-27B-i1-GGUF
ollama run hf.co/mradermacher/HuatuoGPT-3-27B-i1-GGUF:Q4_K_M llama-server -hf mradermacher/HuatuoGPT-3-27B-i1-GGUF:Q4_K_MDownloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get mradermacher/HuatuoGPT-3-27B-i1-GGUF@Q4_K_MThen load it from the LM Studio app or with `lms load`.
vllm serve FreedomIntelligence/HuatuoGPT-3-27Bservices:
vllm:
image: vllm/vllm-openai:latest
command: FreedomIntelligence/HuatuoGPT-3-27B
ports:
- "8000:8000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 8000.
sglang serve FreedomIntelligence/HuatuoGPT-3-27B --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve FreedomIntelligence/HuatuoGPT-3-27B --host 0.0.0.0 --port 30000
ports:
- "30000:30000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 30000.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="FreedomIntelligence/HuatuoGPT-3-27B", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| mradermacher/HuatuoGPT-3-27B-i1-GGUF | GGUF | IQ1_S | 7.1 GB |
| mradermacher/HuatuoGPT-3-27B-i1-GGUF | GGUF | IQ1_M | 7.6 GB |
| mradermacher/HuatuoGPT-3-27B-i1-GGUF | GGUF | IQ2_XXS | 8.4 GB |
| mradermacher/HuatuoGPT-3-27B-i1-GGUF | GGUF | IQ2_XS | 9.1 GB |
| mradermacher/HuatuoGPT-3-27B-i1-GGUF | GGUF | IQ2_S | 9.4 GB |
| mradermacher/HuatuoGPT-3-27B-i1-GGUF | GGUF | IQ2_M | 10 GB |
| mradermacher/HuatuoGPT-3-27B-i1-GGUF | GGUF | Q2_K_S | 10 GB |
| mradermacher/HuatuoGPT-3-27B-i1-GGUF | GGUF | Q2_K | 11 GB |
| mradermacher/HuatuoGPT-3-27B-i1-GGUF | GGUF | IQ3_XXS | 11 GB |
| mradermacher/HuatuoGPT-3-27B-i1-GGUF | GGUF | IQ3_XS | 12 GB |
About HuatuoGPT-3-27B
HuatuoGPT-3-27B is a medical LLM built on Qwen3.8-27B with One-stage Policy Optimization (OnePO). OnePO adapts language models to medicine in a single reinforcement-learning stage, without preceding domain-specific supervised fine-tuning. Teacher responses provide temporary guidance and are retired as the model improves. We release the training code, medical RL dataset, and 8B rubric grader. HuatuoGPT-3 requires thinking mode. Keep enable_thinking=True during inference. The model generates reasoning before providing its final answer after .
Full model card on Hugging Face →Alternatives to HuatuoGPT-3-27B
All alternatives →Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding…
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.
HuatuoGPT-3-27B FAQ
- How much VRAM does HuatuoGPT-3-27B need?
- About 19 GB at Q4_K_M with an 8K context. Q8_0 needs about 31 GB and full precision about 55 GB. Longer contexts need more memory for the KV cache.
- Can HuatuoGPT-3-27B run on the Tesla P40?
- Yes. It fits at Q5_K_M (about 21 GB), at an estimated 9.9 tokens/s. It fits comfortably on the Radeon RX 7900 XTX, Instinct MI50 32GB, RTX 5090.
- Can I use HuatuoGPT-3-27B commercially?
- Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.
- What is the context length of HuatuoGPT-3-27B?
- 262,144 tokens (256K). The full window needs far more memory than an 8K context.
- How do I run HuatuoGPT-3-27B with Ollama or llama.cpp?
- With Ollama: ollama run hf.co/mradermacher/HuatuoGPT-3-27B-i1-GGUF:Q4_K_M. With llama.cpp: llama-server -hf mradermacher/HuatuoGPT-3-27B-i1-GGUF:Q4_K_M, which starts an OpenAI-compatible server.
Rate this model
Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.
0 comments