Instructions to use deepgoyal19/qwen3.5-35b-a3b-code-extract-N128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepgoyal19/qwen3.5-35b-a3b-code-extract-N128 with Transformers:

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

pipe = pipeline("text-generation", model="deepgoyal19/qwen3.5-35b-a3b-code-extract-N128")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepgoyal19/qwen3.5-35b-a3b-code-extract-N128")
model = AutoModelForCausalLM.from_pretrained("deepgoyal19/qwen3.5-35b-a3b-code-extract-N128", 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 deepgoyal19/qwen3.5-35b-a3b-code-extract-N128 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepgoyal19/qwen3.5-35b-a3b-code-extract-N128"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepgoyal19/qwen3.5-35b-a3b-code-extract-N128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepgoyal19/qwen3.5-35b-a3b-code-extract-N128

SGLang

How to use deepgoyal19/qwen3.5-35b-a3b-code-extract-N128 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 "deepgoyal19/qwen3.5-35b-a3b-code-extract-N128" \
    --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": "deepgoyal19/qwen3.5-35b-a3b-code-extract-N128",
		"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 "deepgoyal19/qwen3.5-35b-a3b-code-extract-N128" \
        --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": "deepgoyal19/qwen3.5-35b-a3b-code-extract-N128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepgoyal19/qwen3.5-35b-a3b-code-extract-N128 with Docker Model Runner:
```
docker model run hf.co/deepgoyal19/qwen3.5-35b-a3b-code-extract-N128
```

Qwen3.5-35B-A3B — Coding Extract (N128)

A training-free coding specialist extracted from Qwen/Qwen3.5-35B-A3B by analytically selecting which mixture-of-experts to keep — no fine-tuning, distillation, or gradient updates of any kind. Half the routed experts are removed; the always-on trunk (attention, shared expert, embeddings) is kept whole.

Parameters: 18.54 B (parent: ~34.6 B) — 128 of 256 routed experts kept per layer
Size: 37.1 GB (bf16, model.safetensors)
Derived from: Qwen3.5-35B-A3B (hybrid linear-attention MoE, top-8 routing)
Method: analytic "coupling" expert-selection criterion

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("deepgoyal19/qwen3.5-35b-a3b-code-extract-N128",
                                         torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained("deepgoyal19/qwen3.5-35b-a3b-code-extract-N128")

Recommended coding config (from the parent's card): temperature=0.6, top_p=0.95, top_k=20, repetition_penalty=1.0, thinking mode on.

Evaluation

Benchmark	pass@1
HumanEval	86.6%
HumanEval+	83.5%

Provenance

census_export.json in this repo records the exact keep-set, N, selector, and parity metrics.

Downloads last month: -

Safetensors

Model size

19B params

Tensor type

BF16

Model tree for deepgoyal19/qwen3.5-35b-a3b-code-extract-N128

Base model

Qwen/Qwen3.5-35B-A3B-Base

Finetuned

Qwen/Qwen3.5-35B-A3B

Finetuned

(142)

this model