Instructions to use Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Local Apps Settings

How to use Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ",
		"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/Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ

SGLang

How to use Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ 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 "Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ" \
    --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": "Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ",
		"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 "Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ" \
        --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": "Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ",
		"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 Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ with Docker Model Runner:
```
docker model run hf.co/Vishva007/Qwen3.8-4B-Distill-W4A16-AutoRound-GPTQ
```

Vishva007 commited on 3 days ago

Commit

a854a0c

verified ·

1 Parent(s): d17e456

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

config.json +15 -2
model_extra_tensors.safetensors +2 -2

config.json CHANGED Viewed

@@ -23,7 +23,8 @@
         "bits": 4,
         "group_size": 32,
         "sym": true
-      }
     },
     "group_size": 32,
     "iters": 1000,
@@ -33,7 +34,19 @@
     "static_attention_granularity": "tensor",
     "static_kv_granularity": "tensor",
     "sym": true,
-    "true_sequential": false
   },
   "text_config": {
     "attention_bias": false,

         "bits": 4,
         "group_size": 32,
         "sym": true
+      },
+      "-:.*mtp.*": {}
     },
     "group_size": 32,
     "iters": 1000,
     "static_attention_granularity": "tensor",
     "static_kv_granularity": "tensor",
     "sym": true,
+    "true_sequential": false,
+    "block_name_to_quantize": "model.language_model.layers",
+    "modules_to_not_convert": [
+      "visual",
+      "lm_head",
+      "mtp"
+    ],
+    "extra_config": {
+      ".*mtp.*": {
+        "bits": 16,
+        "data_type": "fp"
+      }
+    }
   },
   "text_config": {
     "attention_bias": false,

model_extra_tensors.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f993d7b896c6d3c72ee66fd446b28bcf316d5f5ce4a0427c0442dfe461cbe1b
-size 241200704

 version https://git-lfs.github.com/spec/v1
+oid sha256:e5fc485d419f2c554169c1fc441f57a1a45a50673bdb4e41d3dd0261b21abe7c
+size 241200736