Instructions to use palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4")
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("palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4")
model = AutoModelForMultimodalLM.from_pretrained("palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4", device_map="auto")
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 palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4",
		"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/palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4

SGLang

How to use palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4 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 "palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4" \
    --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": "palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4",
		"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 "palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4" \
        --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": "palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4",
		"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 palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4 with Docker Model Runner:
```
docker model run hf.co/palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4
```

palmfuture commited on Apr 25

Commit

f32841f

verified ·

1 Parent(s): bddd3f8

Add MTP weights + speculative decoding (backward compatible)

Browse files

- mtp.safetensors: 19 MTP tensors in per-expert split format
(768 expert keys + 17 non-expert, BF16, +1.6 GB)
- model.safetensors.index.json: weight_map updated with 19 MTP keys
(total_size now 24.4 GB)
- config.json: add mlp_only_layers, modules_to_not_convert
(Qwen official schema parity)
- README: document vLLM + SGLang MTP configs with verified metrics

Verified on 4× RTX 3060 12GB:
- vLLM 0.19.1 + MTP: 56-82 t/s, 70-89% acceptance
- vLLM 0.19.1 baseline: works (no regression)
- SGLang 0.5.10 + EAGLE: 52-141 t/s (peak batch), 34-70% acceptance
- SGLang 0.5.10 baseline: works (no regression)

vLLM users with MTP: do NOT pass --quantization moe_wna16 flag
(triggers KeyError in MTP loader; auto-detect required).

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -47,7 +47,7 @@ This v2 release ships **MTP (Multi-Token Prediction) speculative decoding weight
 | Hidden layers | 40 |
 | Context length | 262,144 tokens |
 | Quantization | GPTQ v2, 4-bit, group_size=128, symmetric |
-| Quantized size | 22.7 GB (incl. MTP weights) |
 | KV cache support | fp16, bf16, fp8_e4m3 (storage-only on Ampere) |
 | MTP head | Included (BF16, 785 keys, split per-expert format) |

 | Hidden layers | 40 |
 | Context length | 262,144 tokens |
 | Quantization | GPTQ v2, 4-bit, group_size=128, symmetric |
+| Quantized size | 24.4 GB (incl. MTP weights) |
 | KV cache support | fp16, bf16, fp8_e4m3 (storage-only on Ampere) |
 | MTP head | Included (BF16, 785 keys, split per-expert format) |