Instructions to use jkim96/Qwen3.6-27B-DASHQ-INT3-g128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jkim96/Qwen3.6-27B-DASHQ-INT3-g128 with Transformers:

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

pipe = pipeline("image-text-to-text", model="jkim96/Qwen3.6-27B-DASHQ-INT3-g128", trust_remote_code=True)
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, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("jkim96/Qwen3.6-27B-DASHQ-INT3-g128", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("jkim96/Qwen3.6-27B-DASHQ-INT3-g128", trust_remote_code=True, 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 jkim96/Qwen3.6-27B-DASHQ-INT3-g128 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jkim96/Qwen3.6-27B-DASHQ-INT3-g128"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jkim96/Qwen3.6-27B-DASHQ-INT3-g128",
		"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/jkim96/Qwen3.6-27B-DASHQ-INT3-g128

SGLang

How to use jkim96/Qwen3.6-27B-DASHQ-INT3-g128 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 "jkim96/Qwen3.6-27B-DASHQ-INT3-g128" \
    --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": "jkim96/Qwen3.6-27B-DASHQ-INT3-g128",
		"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 "jkim96/Qwen3.6-27B-DASHQ-INT3-g128" \
        --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": "jkim96/Qwen3.6-27B-DASHQ-INT3-g128",
		"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 jkim96/Qwen3.6-27B-DASHQ-INT3-g128 with Docker Model Runner:
```
docker model run hf.co/jkim96/Qwen3.6-27B-DASHQ-INT3-g128
```

jkim96 commited on May 9

Commit

de8bfc9

verified ·

1 Parent(s): 7d666af

Upload dashq quantized checkpoint (INT3, g128, scale_zero_dtype=float16, zero-shot avg=70.8)

Browse files

Files changed (5) hide show

README.md +13 -10
dashq_config.json +15 -16
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1
model-00004-of-00004.safetensors +1 -1

README.md CHANGED Viewed

@@ -38,6 +38,7 @@ model, tokenizer = load_quantized(
 | Base model | `Qwen/Qwen3.6-27B` |
 | Bits | `3` |
 | Group size | `128` |
 | Calibration dataset | `wikitext2` |
 | Calibration samples | `128` |
 | Sequence length | `2048` |
@@ -48,13 +49,15 @@ model, tokenizer = load_quantized(
 | Metric | Value |
 | --- | ---: |
-| `wikitext2_ppl` | 7.7625 |
-| `arc_challenge` | 59.8123 |
-| `arc_easy` | 77.1044 |
-| `commonsense_qa` | 84.8485 |
-| `hellaswag` | 82.2645 |
-| `lambada_openai` | 75.6647 |
-| `openbookqa` | 45.4000 |
-| `piqa` | 81.9913 |
-| `truthfulqa_mc2` | 54.7219 |
-| `winogrande` | 76.7167 |

 | Base model | `Qwen/Qwen3.6-27B` |
 | Bits | `3` |
 | Group size | `128` |
+| Scale/zero dtype | `float16` |
 | Calibration dataset | `wikitext2` |
 | Calibration samples | `128` |
 | Sequence length | `2048` |
 | Metric | Value |
 | --- | ---: |
+| `wikitext2_ppl` | 7.7554 |
+| `zero-shot accuracy avg` | 70.7634 |
+| `arc_challenge` | 58.7884 |
+| `arc_easy` | 75.5471 |
+| `commonsense_qa` | 86.1589 |
+| `hellaswag` | 82.5931 |
+| `lambada_openai` | 74.7720 |
+| `openbookqa` | 44.8000 |
+| `piqa` | 82.4266 |
+| `truthfulqa_mc2` | 54.9096 |
+| `winogrande` | 76.8745 |

dashq_config.json CHANGED Viewed

@@ -10,6 +10,7 @@
     "low_memory_optimization": false,
     "moe_hessian_scope": "shared",
     "n_samples": 128,
     "symmetric": false,
     "use_error_compensation": true,
     "use_optimal_shrinkage": true,
@@ -5974,20 +5975,18 @@
     "Model": "Qwen/Qwen3.6-27B",
     "ModelSizeGB": 16.513800712,
     "OriginalSizeGB": 55.5630064,
-    "PPL": 7.762491226196289,
-    "Params": "{'bits': 3, 'group_size': 128, 'n_samples': 128, 'moe_hessian_scope': 'shared', 'use_error_compensation': True, 'use_optimal_shrinkage': True, 'use_weighted_quantization': True, 'symmetric': False, 'low_memory_optimization': False}",
-    "QuantTime": 748.9153661727905,
-    "arc_challenge": 59.81228668941979,
-    "arc_easy": 77.10437710437711,
-    "boolq": 81.55963302752293,
-    "commonsense_qa": 84.84848484848484,
-    "hellaswag": 82.26448914558853,
-    "lambada_openai": 75.66466136231321,
-    "openbookqa": 45.4,
-    "piqa": 81.99129488574538,
-    "social_iqa": 73.0749354005168,
-    "truthfulqa_mc2": 54.72186573353546,
-    "winogrande": 76.71665351223362,
-    "zeroshot_avg": 72.10533470088525
   }
-}

     "low_memory_optimization": false,
     "moe_hessian_scope": "shared",
     "n_samples": 128,
+    "scale_zero_dtype": "float16",
     "symmetric": false,
     "use_error_compensation": true,
     "use_optimal_shrinkage": true,
     "Model": "Qwen/Qwen3.6-27B",
     "ModelSizeGB": 16.513800712,
     "OriginalSizeGB": 55.5630064,
+    "PPL": 7.755378246307373,
+    "Params": "{'bits': 3, 'group_size': 128, 'scale_zero_dtype': 'float16', 'n_samples': 128, 'moe_hessian_scope': 'shared', 'use_error_compensation': True, 'use_optimal_shrinkage': True, 'use_weighted_quantization': True, 'symmetric': False, 'low_memory_optimization': False}",
+    "QuantTime": 787.927401304245,
+    "arc_challenge": 58.78839590443686,
+    "arc_easy": 75.54713804713805,
+    "commonsense_qa": 86.15888615888616,
+    "hellaswag": 82.59310894244175,
+    "lambada_openai": 74.77197748884146,
+    "openbookqa": 44.800000000000004,
+    "piqa": 82.4265505984766,
+    "truthfulqa_mc2": 54.909605261997015,
+    "winogrande": 76.87450670876085,
+    "zeroshot_avg": 70.76335212344208
   }
+}

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d1bea86c0ea39d0a6eeb26d86e492089bbaffa3e37dcd0ade1db68c12ee8cb
 size 4970468528

 version https://git-lfs.github.com/spec/v1
+oid sha256:50ccca36e3cedf1d5cbc3f233f1def041f7502c78ae17b133986212d3bdab0e6
 size 4970468528

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce163441bff73002f3fd4df78ebe90cd85e1032376a1920718100b9103ef2ce9
 size 4997537440

 version https://git-lfs.github.com/spec/v1
+oid sha256:14c351d0bdd2510dc0277ea8ec8294cfb80695560daed88e44ad59f97f69e664
 size 4997537440

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c967355c32b68aa0fb2766a790e8362671c2c3a5efa58f2a6531b2facc93526
 size 4002997816

 version https://git-lfs.github.com/spec/v1
+oid sha256:865ffdcd186d481d4e2a7117bebc88f055c47334acab3ee46fd80904d247a869
 size 4002997816