Instructions to use jkim96/Qwen3.6-27B-DASHQ-INT3-g64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jkim96/Qwen3.6-27B-DASHQ-INT3-g64 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-g64", 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-g64", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("jkim96/Qwen3.6-27B-DASHQ-INT3-g64", 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-g64 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-g64"
# 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-g64",
		"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-g64

SGLang

How to use jkim96/Qwen3.6-27B-DASHQ-INT3-g64 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-g64" \
    --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-g64",
		"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-g64" \
        --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-g64",
		"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-g64 with Docker Model Runner:
```
docker model run hf.co/jkim96/Qwen3.6-27B-DASHQ-INT3-g64
```

jkim96 commited on May 9

Commit

bd8ca46

verified ·

1 Parent(s): 5b3f20b

Upload dashq quantized checkpoint (INT3, g64, scale_zero_dtype=float16, zero-shot avg=70.6)

Browse files

Files changed (5) hide show

README.md +11 -9
dashq_config.json +14 -14
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 | `64` |
 | Calibration dataset | `wikitext2` |
 | Calibration samples | `128` |
 | Sequence length | `2048` |
@@ -48,14 +49,15 @@ model, tokenizer = load_quantized(
 | Metric | Value |
 | --- | ---: |
-| `wikitext2_ppl` | 7.7746 |
-| `arc_challenge` | 60.7509 |
-| `arc_easy` | 79.2929 |
-| `commonsense_qa` | 63.1450 |
-| `hellaswag` | 82.3442 |
-| `lambada_openai` | 74.6167 |
-| `openbookqa` | 44.8000 |
-| `piqa` | 82.0457 |
-| `truthfulqa_mc2` | 54.7740 |
 | `winogrande` | 76.9534 |

 | Base model | `Qwen/Qwen3.6-27B` |
 | Bits | `3` |
 | Group size | `64` |
+| Scale/zero dtype | `float16` |
 | Calibration dataset | `wikitext2` |
 | Calibration samples | `128` |
 | Sequence length | `2048` |
 | Metric | Value |
 | --- | ---: |
+| `wikitext2_ppl` | 7.7131 |
+| `zero-shot accuracy avg` | 70.5799 |
+| `arc_challenge` | 60.1536 |
+| `arc_easy` | 78.4512 |
+| `commonsense_qa` | 79.4431 |
+| `hellaswag` | 81.8861 |
+| `lambada_openai` | 75.1213 |
+| `openbookqa` | 45.4000 |
+| `piqa` | 81.8825 |
+| `truthfulqa_mc2` | 55.9281 |
 | `winogrande` | 76.9534 |

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,
@@ -5974,19 +5975,18 @@
     "Model": "Qwen/Qwen3.6-27B",
     "ModelSizeGB": 17.27475596,
     "OriginalSizeGB": 55.5630064,
-    "PPL": 7.774606227874756,
-    "Params": "{'bits': 3, 'group_size': 64, '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": 884.1916358470917,
-    "arc_challenge": 60.75085324232082,
-    "arc_easy": 79.29292929292929,
-    "boolq": 67.55351681957187,
-    "commonsense_qa": 63.14496314496314,
-    "hellaswag": 82.34415455088627,
-    "lambada_openai": 74.61672811954202,
-    "openbookqa": 44.800000000000004,
-    "piqa": 82.04570184983679,
-    "social_iqa": 68.3204134366925,
-    "truthfulqa_mc2": 54.774021091223176,
-    "winogrande": 76.95343330702447
   }
 }

     "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": 17.27475596,
     "OriginalSizeGB": 55.5630064,
+    "PPL": 7.71309757232666,
+    "Params": "{'bits': 3, 'group_size': 64, '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": 894.5826256275177,
+    "arc_challenge": 60.153583617747444,
+    "arc_easy": 78.45117845117845,
+    "commonsense_qa": 79.44307944307944,
+    "hellaswag": 81.88607847042422,
+    "lambada_openai": 75.12128856976518,
+    "openbookqa": 45.4,
+    "piqa": 81.88248095756256,
+    "truthfulqa_mc2": 55.9280749996677,
+    "winogrande": 76.95343330702447,
+    "zeroshot_avg": 70.57991086849438
   }
 }

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb4da5b9691b1b833ed3c930800378c7ad5315b367b287951099cb3120969c3
 size 4968942552

 version https://git-lfs.github.com/spec/v1
+oid sha256:69e03e3443d8fe5513a46fb33c09b94c8ec6122ec0d06534756a879471533a67
 size 4968942552

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa75309016b9f6260412b783767e747d9286f496a952b64c1542801c7522a7ad
 size 4995401320

 version https://git-lfs.github.com/spec/v1
+oid sha256:cfb922d084d81c3cbecdc222c7a1112957077d6f88b09ae5978e87d0d2f71bb5
 size 4995401320

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e27298c29c957fab5490ce7019c8d54f656797a66962f64492efa7fd4a8b1e5
 size 4767615160

 version https://git-lfs.github.com/spec/v1
+oid sha256:52686153606d162c95b2276e99ba1532b6202e92687ef264f748700f773cb281
 size 4767615160