Instructions to use schoggie/Qwen3.6-35B-A3B-java-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use schoggie/Qwen3.6-35B-A3B-java-v1 with Transformers:

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

pipe = pipeline("text-generation", model="schoggie/Qwen3.6-35B-A3B-java-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("schoggie/Qwen3.6-35B-A3B-java-v1")
model = AutoModelForCausalLM.from_pretrained("schoggie/Qwen3.6-35B-A3B-java-v1")
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 schoggie/Qwen3.6-35B-A3B-java-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "schoggie/Qwen3.6-35B-A3B-java-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schoggie/Qwen3.6-35B-A3B-java-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/schoggie/Qwen3.6-35B-A3B-java-v1

SGLang

How to use schoggie/Qwen3.6-35B-A3B-java-v1 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 "schoggie/Qwen3.6-35B-A3B-java-v1" \
    --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": "schoggie/Qwen3.6-35B-A3B-java-v1",
		"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 "schoggie/Qwen3.6-35B-A3B-java-v1" \
        --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": "schoggie/Qwen3.6-35B-A3B-java-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use schoggie/Qwen3.6-35B-A3B-java-v1 with Docker Model Runner:
```
docker model run hf.co/schoggie/Qwen3.6-35B-A3B-java-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3.6-35B-A3B-java-v1

QLoRA fine-tune of Qwen/Qwen3.6-35B-A3B targeting agentic Java coding and long-context positional recall.

GGUF quantizations live at schoggie/Qwen3.6-35B-A3B-java-v1-GGUF.

Training


Base	Qwen/Qwen3.6-35B-A3B (35B total / 3B active MoE, 256 experts, 8 active)
Method	QLoRA, r=32, target modules `q/k/v/o/gate/up/down_proj`
Trainable params	16.7 M (0.048 % of total)
Hardware	2 × A100 80 GB PCIe (RunPod), single-process model parallelism via `device_map="auto"`
Steps	528 (~10 h 17 min wall clock)
Final loss	1.39 → 0.27 (cosine schedule, mean token accuracy 87 %)
Dataset	4039 train + 51 eval rows, hybrid agentic-Java + positional-recall (DeepSeek + synthetic recall). Private.

Evaluation

40-example short-recall held-out set, compared against base Qwen3.6-35B-A3B at Q4_K_M on the same hardware:

Metric	Base Q4_K_M	Fine-tuned Q4_K_M	Δ
Avg grey/20	5.55	6.53	+18 %
Passed (≥ 8 grey)	11 / 40	14 / 40	+3 (+27 %)

Per-row breakdown: 13 improved, 15 tied, 12 worsened. The +3-pass go/no-go threshold for the pilot was met.

Intended use

Java code generation in agentic loops (multi-step tool use, file edits, recall across large project context).
Long-context Java retrieval — fine-tune emphasizes attending to relevant identifiers across ≥ 32 K-token windows.
Drop-in replacement for the base in any Qwen3.6-A3B serving stack (llama.cpp, vLLM, sglang once supported).

Limitations

Single-language fine-tune (English prompts, Java code). Other-language behaviour likely unchanged from base, untested.
Eval was on a 40-row short-recall set; broader benchmarks (HumanEval-Java, SWE-bench, MMLU) were not re-run.
Trained on Qwen 3.6 A3B specifically; not validated on the dense-7B variant or larger A22B sibling.

Inference

transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("schoggie/Qwen3.6-35B-A3B-java-v1")
model = AutoModelForCausalLM.from_pretrained(
    "schoggie/Qwen3.6-35B-A3B-java-v1",
    torch_dtype="auto",
    device_map="auto",
)

llama.cpp / Ollama / LM Studio

Use the GGUF repo: schoggie/Qwen3.6-35B-A3B-java-v1-GGUF. Q6_K is the production-deployed quant on the maintainer's dual-V100 box (27 GB, ~lossless).

Note on llama.cpp loader. Stock upstream llama.cpp has known loader bugs on the Qwen3.6-A3B GGUF metadata path. Use the unsloth-maintained fork until the upstream patch lands.

License

Inherits the Qwen Research License from the base model. The fine-tune adapter and merged weights are released under the same terms.

Citation

@misc{qwen36-a3b-java-v1,
  author = {schoggie},
  title  = {qwen36-a3b-java-v1: Java-agentic QLoRA fine-tune of Qwen3.6-35B-A3B},
  year   = {2026},
  url    = {https://huggingface.co/schoggie/Qwen3.6-35B-A3B-java-v1}
}

Downloads last month: 21

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for schoggie/Qwen3.6-35B-A3B-java-v1

Base model

Qwen/Qwen3.6-35B-A3B

Adapter

(24)

this model

Quantizations

1 model