Instructions to use maci0/Qwopus3.6-27B-Coder-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maci0/Qwopus3.6-27B-Coder-NVFP4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="maci0/Qwopus3.6-27B-Coder-NVFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("maci0/Qwopus3.6-27B-Coder-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("maci0/Qwopus3.6-27B-Coder-NVFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use maci0/Qwopus3.6-27B-Coder-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maci0/Qwopus3.6-27B-Coder-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maci0/Qwopus3.6-27B-Coder-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/maci0/Qwopus3.6-27B-Coder-NVFP4

SGLang

How to use maci0/Qwopus3.6-27B-Coder-NVFP4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "maci0/Qwopus3.6-27B-Coder-NVFP4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maci0/Qwopus3.6-27B-Coder-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "maci0/Qwopus3.6-27B-Coder-NVFP4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maci0/Qwopus3.6-27B-Coder-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use maci0/Qwopus3.6-27B-Coder-NVFP4 with Docker Model Runner:
```
docker model run hf.co/maci0/Qwopus3.6-27B-Coder-NVFP4
```

Qwopus3.6-27B-Coder-NVFP4 / README.md

maci0

Add Ornith-35B MoE abliterated to Related siblings

63e998b verified 4 days ago

preview code

Raw

History Blame Contribute Delete

12.7 kB

	---
	base_model: Jackrong/Qwopus3.6-27B-Coder
	base_model_relation: quantized
	license: apache-2.0
	library_name: transformers
	pipeline_tag: image-text-to-text
	language:
	- en
	- zh
	tags:
	- nvfp4
	- fp4
	- w4a4
	- gptq
	- quantized
	- compressed-tensors
	- llm-compressor
	- vllm
	- qwen3_5
	- vision-language
	- thinking
	- code
	- coder
	---

	<div style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; border: 1px solid #cbd5e1; border-radius: 16px; box-shadow: 0 10px 15px -3px rgba(0,0,0,0.08); overflow: hidden; margin-bottom: 26px;">
	<div style="background: linear-gradient(135deg, #7c3aed 0%, #4c1d95 100%); padding: 26px; color: white;">
	<div style="font-size: 11px; font-weight: 800; letter-spacing: 1.5px; text-transform: uppercase; color: #ddd6fe; margin-bottom: 12px;">◆ <a href="https://huggingface.co/spaces/maci0/rogue-quants" style="color: #ddd6fe; text-decoration: none;">Rogue Quants</a> · NVFP4</div>
	<div style="display: flex; align-items: center; justify-content: space-between; flex-wrap: wrap; gap: 10px;">
	<h1 style="margin: 0; font-size: 25px; font-weight: 800; display: flex; align-items: center; gap: 12px; color: white; border: none;">🪐 Qwopus3.6-27B-Coder · NVFP4</h1>
	<span style="background: #10b981; color: white; font-size: 11px; font-weight: 800; padding: 5px 12px; border-radius: 20px; text-transform: uppercase; letter-spacing: 0.5px;">💻 Coder</span>
	</div>
	<p style="margin: 10px 0 0 0; font-size: 14px; color: #ddd6fe; font-weight: 500;">27B coder vision-language · agentic + tool-calling · thinking · GPTQ NVFP4 W4A4</p>
	</div>
	<div style="display: flex; gap: 8px; flex-wrap: wrap; padding: 13px 24px; background: #faf5ff; border-bottom: 1px solid #e9d5ff;">
	<span style="background: #f3e8ff; color: #6b21a8; font-size: 11px; font-weight: 700; padding: 4px 11px; border-radius: 20px; border: 1px solid #e9d5ff;">⚙️ NVFP4 · W4A4</span>
	<span style="background: #f3e8ff; color: #6b21a8; font-size: 11px; font-weight: 700; padding: 4px 11px; border-radius: 20px; border: 1px solid #e9d5ff;">💾 ~18 GB</span>
	<span style="background: #f3e8ff; color: #6b21a8; font-size: 11px; font-weight: 700; padding: 4px 11px; border-radius: 20px; border: 1px solid #e9d5ff;">📉 PPL 6.63</span>
	<span style="background: #f3e8ff; color: #6b21a8; font-size: 11px; font-weight: 700; padding: 4px 11px; border-radius: 20px; border: 1px solid #e9d5ff;">📐 256K context</span>
	<span style="background: #f3e8ff; color: #6b21a8; font-size: 11px; font-weight: 700; padding: 4px 11px; border-radius: 20px; border: 1px solid #e9d5ff;">🚀 vLLM · Blackwell</span>
	<span style="background: #ede9fe; color: #5b21b6; font-size: 11px; font-weight: 700; padding: 4px 11px; border-radius: 20px; border: 1px solid #ddd6fe;">💻 Coder</span>
	<span style="background: #dcfce7; color: #166534; font-size: 11px; font-weight: 700; padding: 4px 11px; border-radius: 20px; border: 1px solid #bbf7d0;">🛠️ Tool-calling</span>
	</div>
	<div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(150px, 1fr)); gap: 14px; padding: 20px 24px; background: #ffffff;">
	<div style="border: 1px solid #e9d5ff; padding: 14px; border-radius: 10px; background: #faf5ff; text-align: center;">
	<span style="font-size: 11px; font-weight: 800; color: #7c3aed; text-transform: uppercase; display: block; margin-bottom: 6px; letter-spacing: 0.5px;">Size on disk</span>
	<span style="font-size: 24px; font-weight: 900; color: #4c1d95; display: block; line-height: 1;">18 GB</span>
	<span style="font-size: 12px; color: #64748b; font-weight: 600;">vs 55.6 GB bf16 (~33%)</span>
	</div>
	<div style="border: 1px solid #e9d5ff; padding: 14px; border-radius: 10px; background: #faf5ff; text-align: center;">
	<span style="font-size: 11px; font-weight: 800; color: #7c3aed; text-transform: uppercase; display: block; margin-bottom: 6px; letter-spacing: 0.5px;">wikitext-2 PPL</span>
	<span style="font-size: 24px; font-weight: 900; color: #4c1d95; display: block; line-height: 1;">6.63</span>
	<span style="font-size: 12px; color: #64748b; font-weight: 600;">near-lossless vs bf16</span>
	</div>
	<div style="border: 1px solid #e9d5ff; padding: 14px; border-radius: 10px; background: #faf5ff; text-align: center;">
	<span style="font-size: 11px; font-weight: 800; color: #7c3aed; text-transform: uppercase; display: block; margin-bottom: 6px; letter-spacing: 0.5px;">Context</span>
	<span style="font-size: 24px; font-weight: 900; color: #4c1d95; display: block; line-height: 1;">256K</span>
	<span style="font-size: 12px; color: #64748b; font-weight: 600;">262144 tokens</span>
	</div>
	<div style="border: 1px solid #e9d5ff; padding: 14px; border-radius: 10px; background: #faf5ff; text-align: center;">
	<span style="font-size: 11px; font-weight: 800; color: #7c3aed; text-transform: uppercase; display: block; margin-bottom: 6px; letter-spacing: 0.5px;">Scheme</span>
	<span style="font-size: 24px; font-weight: 900; color: #4c1d95; display: block; line-height: 1;">NVFP4</span>
	<span style="font-size: 12px; color: #64748b; font-weight: 600;">W4A4 · GPTQ + MSE</span>
	</div>
	</div>
	</div>

	TL;DR: Qwopus3.6-27B-Coder, quantized to NVFP4 (W4A4) for vLLM on NVIDIA Blackwell. 18 GB, wikitext-2 PPL 6.63, 256K agentic coder.

	# Qwopus3.6-27B-Coder NVFP4

	NVFP4 (W4A4) quantization of
	[Jackrong/Qwopus3.6-27B-Coder](https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder),
	packed in the `compressed-tensors` `nvfp4-pack-quantized` format with
	[llm-compressor](https://github.com/vllm-project/llm-compressor). Weights are
	quantized with GPTQ (error-compensated rounding) and an MSE observer, on a
	domain-matched calibration blend that includes code.

	Near-lossless. Fused layers (q/k/v, gate/up) share one NVFP4 global scale, so vLLM
	loads it cleanly with no per-layer-scale warning or fallback. wikitext-2 perplexity for
	this build: 6.63.

	- About 18 GB on disk versus about 55.6 GB for the bf16 source (about 33%).
	- Built for vLLM on NVIDIA Blackwell, where both the 4-bit weight and 4-bit activation
	paths are accelerated. On pre-Blackwell GPUs vLLM runs it weight-only.
	- Loading and generation verified in vLLM v0.23.0 on an NVIDIA GB10 (Blackwell, sm_121).

	## Fidelity

	Near-lossless versus the bf16 source: wikitext-2 perplexity for this build is 6.63.

	\| Metric \| Value \|
	\|---\|---\|
	\| wikitext-2 PPL \| 6.63 \|
	\| Weights \| NVFP4 W4A4, group 16 \|
	\| Size \| 18 GB vs 55.6 GB bf16 (~33%) \|

	NVFP4 uses GPTQ error compensation, an MSE observer, and shared fused-layer scales, so the
	drop from bf16 is minimal.

	## Quickstart

	NVFP4 is auto-detected from `config.json` (`compressed-tensors`); no quantization flag
	needed. `--reasoning-parser qwen3` splits the `<think>` block into `reasoning_content`;
	`--tool-call-parser qwen3_coder` enables tool/function calling for agentic coding.

	```bash
	vllm serve maci0/Qwopus3.6-27B-Coder-NVFP4 \
	--served-model-name qwopus-27b-coder-nvfp4 \
	--max-model-len 131072 \
	--gpu-memory-utilization 0.90 \
	--kv-cache-dtype fp8 \
	--reasoning-parser qwen3 \
	--enable-auto-tool-choice --tool-call-parser qwen3_coder
	```

	- Supports up to 262144 tokens; keep at least 128K to preserve thinking quality.
	`--max-model-len 131072` is a safe default; raise it if memory allows.
	- Add `--language-model-only` to skip the vision tower and free KV cache for text use.
	- The parser flags are not auto-detected; pass them explicitly.

	### Python (OpenAI client)

	```python
	from openai import OpenAI
	client = OpenAI(base_url="http://localhost:8000/v1", api_key="x")
	r = client.chat.completions.create(
	model="qwopus-27b-coder-nvfp4",
	messages=[{"role": "user", "content": "Write a Python function that merges two sorted lists."}],
	)
	print(r.choices[0].message.content)
	```

	### curl

	```bash
	curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
	"model": "qwopus-27b-coder-nvfp4",
	"messages": [{"role": "user", "content": "Write a Python function that merges two sorted lists."}]
	}'
	```

	## About the base model

	A 27B Qwen3.5-family vision-language model specialized for code (Qwopus 3.6 Coder),
	with thinking-mode reasoning and a 256K context window.

	- 64 decoder layers: hybrid gated delta-net linear attention plus full attention, dense
	MLP, plus a vision tower for image and video input.
	- 256K context (`max_position_embeddings` 262144).
	- Thinking mode by default, with an instruct toggle.

	## Quantization

	\| \| \|
	\|---\|---\|
	\| Scheme \| NVFP4, W4A4 \|
	\| Weight rounding \| GPTQ (Hessian-based error compensation), MSE observer \|
	\| Weights \| FP4 (E2M1), `group_size=16`, `tensor_group`, FP8 (E4M3) group scales, shared across fused layers \|
	\| Activations \| FP4, dynamic per-group, FP8 (E4M3) scales \|
	\| Quantized \| all language-model `Linear` layers \|
	\| Kept in bf16 \| vision tower (`model.visual.*`), `lm_head`, MTP head \|
	\| Untouched \| gated delta-net `Conv1d` and SSM params (`A_log`, `dt_bias`), never `Linear` \|

	GPTQ is a quantization-time cost only; inference speed and format are identical to
	plain round-to-nearest NVFP4, but it chooses better 4-bit values.

	Calibration: 512 domain-matched samples (long reasoning + general chat + code),
	`max_seq_len=2048`, text-only path through the VL model.

	## Recommended sampling

	Thinking mode is the default.

	- Thinking, precise coding: `temperature=0.6`, `top_p=0.95`, `top_k=20`
	- Thinking, general: `temperature=1.0`, `top_p=0.95`, `top_k=20`
	- Instruct / non-thinking: `temperature=0.7`, `top_p=0.80`, `top_k=20`
	- To run non-thinking, set `{%- set enable_thinking = false %}` in the chat template, or
	pass `extra_body={"chat_template_kwargs": {"enable_thinking": false}}`.

	## Reproduction

	Toolchain: `llmcompressor==0.12.0`, `compressed-tensors==0.17.1`, `transformers==5.12.1`,
	`torch==2.11.0+cu130`, on an NVIDIA GB10 (Blackwell, sm_121). llm-compressor 0.12 shares
	the NVFP4 global scale across fused layers automatically (q/k/v, gate/up).

	## Related

	- Base model: [Jackrong/Qwopus3.6-27B-Coder](https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder)
	- Space: [Rogue Quants](https://huggingface.co/spaces/maci0/rogue-quants)
	- Collection: [NVFP4 Quants](https://huggingface.co/collections/maci0/nvfp4-quants-gb10-blackwell-6a446fc03174db196e436339)
	- Sibling NVFP4 quants:
	- [Qwopus3.6-27B-Coder abliterated](https://huggingface.co/maci0/Qwopus3.6-27B-Coder-abliterated-NVFP4) (the abliterated version)
	- [Qwopus3.6-27B-v2 abliterated](https://huggingface.co/maci0/Qwopus3.6-27B-v2-abliterated-NVFP4)
	- [Ornith-1.0-35B MoE abliterated](https://huggingface.co/maci0/Ornith-1.0-35B-abliterated-NVFP4)
	- [Qwen3.6-40B Deckard](https://huggingface.co/maci0/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NVFP4)
	- [Huihui-Qwythos-9B Claude-Mythos](https://huggingface.co/maci0/Huihui-Qwythos-9B-Claude-Mythos-5-1M-abliterated-NVFP4)
	- [Ornith-1.0-9B abliterated](https://huggingface.co/maci0/Ornith-1.0-9B-abliterated-NVFP4)

	## Notes

	- Needs NVIDIA Blackwell (sm_121, e.g. GB10) for accelerated W4A4; pre-Blackwell GPUs run it weight-only.
	- `--reasoning-parser` and `--tool-call-parser` are not auto-detected; pass them explicitly.
	- Thinking mode is on by default; toggle it via the chat template or `chat_template_kwargs`.

	## License

	Apache-2.0, following the base model. Intended use and all responsibility for use follow
	the base model.

	## Credits

	- Base model: [Jackrong](https://huggingface.co/Jackrong)
	- Quantization tooling: [llm-compressor](https://github.com/vllm-project/llm-compressor) / [compressed-tensors](https://github.com/neuralmagic/compressed-tensors)

	<div style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; border: 1px solid #e9d5ff; border-left: 5px solid #7c3aed; border-radius: 0 12px 12px 0; background: #faf5ff; padding: 16px 20px; margin-top: 28px; font-size: 13px; color: #334155; line-height: 1.6;">
	Part of <a href="https://huggingface.co/spaces/maci0/rogue-quants" style="color: #6d28d9; font-weight: 700; text-decoration: none;">🎲 Rogue Quants</a>, a set of NVFP4 (W4A4) quants for vLLM on Blackwell. See the full <a href="https://huggingface.co/collections/maci0/nvfp4-quants-gb10-blackwell-6a446fc03174db196e436339" style="color: #6d28d9; font-weight: 700; text-decoration: none;">NVFP4 Quants collection</a>.
	<br>Built on NVIDIA GB10 (Blackwell, sm_121) with llm-compressor · GPTQ + MSE · shared fused-layer scales.
	</div>