Instructions to use mssfj/Qwen3.5-9B-GPTQ-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mssfj/Qwen3.5-9B-GPTQ-INT8 with Transformers:

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

pipe = pipeline("text-generation", model="mssfj/Qwen3.5-9B-GPTQ-INT8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mssfj/Qwen3.5-9B-GPTQ-INT8")
model = AutoModelForCausalLM.from_pretrained("mssfj/Qwen3.5-9B-GPTQ-INT8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mssfj/Qwen3.5-9B-GPTQ-INT8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mssfj/Qwen3.5-9B-GPTQ-INT8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mssfj/Qwen3.5-9B-GPTQ-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mssfj/Qwen3.5-9B-GPTQ-INT8

SGLang

How to use mssfj/Qwen3.5-9B-GPTQ-INT8 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 "mssfj/Qwen3.5-9B-GPTQ-INT8" \
    --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": "mssfj/Qwen3.5-9B-GPTQ-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "mssfj/Qwen3.5-9B-GPTQ-INT8" \
        --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": "mssfj/Qwen3.5-9B-GPTQ-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mssfj/Qwen3.5-9B-GPTQ-INT8 with Docker Model Runner:
```
docker model run hf.co/mssfj/Qwen3.5-9B-GPTQ-INT8
```

Qwen3.5-9B-GPTQ-INT8 / README.md

mssfj

Upload README.md with huggingface_hub

aa84aea verified 3 months ago

preview code

Raw

History Blame Contribute Delete

1.7 kB

metadata

language:
  - en
license: apache-2.0
base_model: Qwen/Qwen3.5-9B
tags:
  - qwen
  - gptq
  - quantized
  - math
  - causal-lm
library_name: transformers
pipeline_tag: text-generation

Qwen3.5-9B-GPTQ-INT8

This model is a GPTQ-quantized version of Qwen/Qwen3.5-9B with a normalized text-only config.json.

Quantization

Method: GPTQ
Bits: 8
Group size: 128
desc_act: False
damp_percent: 0.1
Calibration preset: math_qa_cot
Calibration dataset: zwhe99/DeepMath-103K split train
Max calibration samples: 128
Max sequence length: 16384

Reproduction

uv run python quantization/quantize_qwen35_9b_gptq.py \
  --model-name Qwen/Qwen3.5-9B \
  --output-dir /workspace/lowbit-math-reasoning/experiments/models/Qwen3.5-9B-GPTQ-INT8 \
  --dataset-name zwhe99/DeepMath-103K \
  --dataset-config '' \
  --dataset-split train \
  --calibration-preset math_qa_cot \
  --question-column question \
  --answer-column r1_solution_1 \
  --text-column r1_solution_1 \
  --max-calibration-samples 128 \
  --max-seq-len 16384 \
  --bits 8 \
  --group-size 128 \
  --damp-percent 0.1

The current quantization script rewrites config.json after save_pretrained() so the exported checkpoint uses the same text-only qwen3_5_text layout as the working INT4 checkpoint.

Validation

This normalized-config checkpoint was re-evaluated on GSM8K and matched the original INT8 accuracy while improving throughput substantially.

Original INT8: EM 0.96, 105.98 tok/s
Fixed-config INT8: EM 0.96, 150.84 tok/s

Notes

This repository contains quantized weights only.
The checkpoint is intended for text-only evaluation.
vLLM loads this checkpoint as gptq_marlin.