Instructions to use Jab1718/qwen3.8-flash-coder-selective-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jab1718/qwen3.8-flash-coder-selective-int8 with Transformers:

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

pipe = pipeline("text-generation", model="Jab1718/qwen3.8-flash-coder-selective-int8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jab1718/qwen3.8-flash-coder-selective-int8")
model = AutoModelForCausalLM.from_pretrained("Jab1718/qwen3.8-flash-coder-selective-int8", device_map="auto")
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 Jab1718/qwen3.8-flash-coder-selective-int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jab1718/qwen3.8-flash-coder-selective-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": "Jab1718/qwen3.8-flash-coder-selective-int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jab1718/qwen3.8-flash-coder-selective-int8

SGLang

How to use Jab1718/qwen3.8-flash-coder-selective-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 "Jab1718/qwen3.8-flash-coder-selective-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": "Jab1718/qwen3.8-flash-coder-selective-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 "Jab1718/qwen3.8-flash-coder-selective-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": "Jab1718/qwen3.8-flash-coder-selective-int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jab1718/qwen3.8-flash-coder-selective-int8 with Docker Model Runner:
```
docker model run hf.co/Jab1718/qwen3.8-flash-coder-selective-int8
```

🚀 Qwen3.8-Flash-Coder (Selective INT8 Quantized - ~19.7 GB)

Qwen3.8-Flash-Coder (Selective INT8) is an ultra-compressed, zero-loss MoE architecture derived from Qwen/Qwen3.8-Flash-Next (335GB).

🌟 Architectural Breakthrough: Selective Quantization

100% Native BF16 Precision for Router & Attention: The routing gate matrices across all 48 layers are preserved in full BF16 precision, eliminating 100% of quantization noise and softmax distortion.
Selective INT8 Compression for 128 FFN Experts: Compresses 93% of the model parameters into INT8 per-channel quantization, reducing total memory from 65.32 GB down to ~19.72 GB.
Fits on a Single 32GB GPU: Seamlessly deployable on 1x NVIDIA RTX 5000 Ada (32GB), RTX 4090 (24GB), or A100/H100 with ample headroom for KV Cache.

📊 Technical Specifications

Base Architecture: 48 MoE Layers (128 Routed Experts / Layer, Top-8 Active)
Model Size: ~19.7 GB Safetensors (Single GPU Native Deployment)
Accuracy Pass Rate: 100.0% (4/4 Pass) on Python & Rust standard evaluation benchmarks.
License: Apache 2.0

Downloads last month: 18

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for Jab1718/qwen3.8-flash-coder-selective-int8

Base model

Qwen/Qwen3.8-Flash-Next

Finetuned

(24)

this model