Instructions to use bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF",
	filename="Qwen3.5-9b-Sushi-Coder-RL.BF16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M

Ollama
How to use bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF with Ollama:
```
ollama run hf.co/bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M
```

Unsloth Studio

How to use bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF to start chatting

How to use bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF with Docker Model Runner:
```
docker model run hf.co/bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M
```

Lemonade

How to use bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-9b-Sushi-Coder-RL-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.5-9b-Sushi-Coder-RL-GGUF

Lineage

Base model lineage: bigatuna/Qwen3.5-9b-Sushi-Coder
RL model: bigatuna/Qwen3.5-9b-Sushi-Coder-RL
RL pipeline: NousResearch/atropos

Training

The upstream SFT model was trained with Unsloth on:

The RL stage was then run for coding with NousResearch/hermes-agent using NousResearch/atropos.

During that run, vLLM was patched with vllm-project/vllm PR #36395, fix(lora): add bounds checking for TP configurations, to address the LoRA tensor-parallel bounds issue.

Files

Qwen3.5-9b-Sushi-Coder-RL.Q4_K_M.gguf
Qwen3.5-9b-Sushi-Coder-RL.Q8_0.gguf
Qwen3.5-9b-Sushi-Coder-RL.BF16-mmproj.gguf

Usage Note

This is a multimodal Qwen 3.5 export. Use the text GGUF together with the BF16-mmproj file.

Quick Start

Example download commands with the Hugging Face CLI:

hf download bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF \
  Qwen3.5-9b-Sushi-Coder-RL.Q4_K_M.gguf \
  Qwen3.5-9b-Sushi-Coder-RL.BF16-mmproj.gguf

Alternative quant:

hf download bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF \
  Qwen3.5-9b-Sushi-Coder-RL.Q8_0.gguf \
  Qwen3.5-9b-Sushi-Coder-RL.BF16-mmproj.gguf

Metadata

License: Apache-2.0
Architecture: Qwen 3.5
Format: GGUF
Tags: llama.cpp, qwen3_5, multimodal, code, rl, conversational

LiveCodeBench Evaluation

The benchmark results below were produced from matched local BF16 vLLM endpoints so the RL model and the base model were evaluated with the same serving method, the same task, and the same generation settings.

Evaluated models:

RL model: bigatuna/Qwen3.5-9b-Sushi-Coder-RL
Base model: Qwen/Qwen3.5-9B

Matched benchmark setup:

Task: lcb:codegeneration|0
Benchmark size: 268 problems
Backend: lighteval endpoint litellm
Context length: 4096
vLLM dtype: bfloat16
Same max_new_tokens, same prompt/task, same serving stack, same evaluation harness

Matched Full Results

Deterministic run:

temperature=0.0
top_p=1.0
seed=0
max_new_tokens=1024

Results:

RL model: codegen_pass@1:16 = 0.2015 +/- 0.0245
Base model: codegen_pass@1:16 = 0.0336 +/- 0.0110

Approximate passes:

RL model: 54 / 268
Base model: 9 / 268

Sampling run:

temperature=0.6
top_p=0.95
top_k=20
min_p=0.0
presence_penalty=0.0
repetition_penalty=1.0
max_new_tokens=1024

Results:

RL model: codegen_pass@1:16 = 0.2388 +/- 0.0261
Base model: codegen_pass@1:16 = 0.0261 +/- 0.0098

Approximate passes:

RL model: 64 / 268
Base model: 7 / 268

In both matched full runs, the RL model outperformed the base model by a wide margin.

Exact Reproduction Commands

These are the exact command shapes used for the matched local evaluation.

1. Start the RL endpoint

export CUDA_VISIBLE_DEVICES=1
vllm serve \
  <PATH_TO_YOUR_RL_MERGED_MODEL> \
  --host 0.0.0.0 \
  --port 9001 \
  --served-model-name bigatuna/Qwen3.5-9b-Sushi-Coder-RL \
  --max-model-len 4096 \
  --dtype bfloat16 \
  --gpu-memory-utilization 0.45

2. Start the base endpoint

export CUDA_VISIBLE_DEVICES=0
vllm serve \
  Qwen/Qwen3.5-9B \
  --host 0.0.0.0 \
  --port 9002 \
  --served-model-name Qwen/Qwen3.5-9B \
  --max-model-len 4096 \
  --dtype bfloat16 \
  --gpu-memory-utilization 0.45

3. Deterministic matched run

RL model:

cat > /tmp/lighteval_rl.yaml <<'EOF'
model_parameters:
  provider: "openai"
  model_name: "openai/bigatuna/Qwen3.5-9b-Sushi-Coder-RL"
  base_url: "http://localhost:9001/v1"
  api_key: "dummy"
  generation_parameters:
    temperature: 0.0
    max_new_tokens: 1024
    top_p: 1.0
    seed: 0
EOF

lighteval endpoint litellm \
  /tmp/lighteval_rl.yaml \
  'lcb:codegeneration|0' \
  --output-dir /tmp/lcb_rl_full \
  --save-details

Base model:

cat > /tmp/lighteval_base.yaml <<'EOF'
model_parameters:
  provider: "openai"
  model_name: "openai/Qwen/Qwen3.5-9B"
  base_url: "http://localhost:9002/v1"
  api_key: "dummy"
  generation_parameters:
    temperature: 0.0
    max_new_tokens: 1024
    top_p: 1.0
    seed: 0
EOF

lighteval endpoint litellm \
  /tmp/lighteval_base.yaml \
  'lcb:codegeneration|0' \
  --output-dir /tmp/lcb_base_full \
  --save-details

4. Temperature 0.6 matched run

RL model:

cat > /tmp/lighteval_rl_t06.yaml <<'EOF'
model_parameters:
  provider: "openai"
  model_name: "openai/bigatuna/Qwen3.5-9b-Sushi-Coder-RL"
  base_url: "http://localhost:9001/v1"
  api_key: "dummy"
  generation_parameters:
    temperature: 0.6
    max_new_tokens: 1024
    top_p: 0.95
    top_k: 20
    min_p: 0.0
    presence_penalty: 0.0
    repetition_penalty: 1.0
EOF

lighteval endpoint litellm \
  /tmp/lighteval_rl_t06.yaml \
  'lcb:codegeneration|0' \
  --output-dir /tmp/lcb_rl_full_t06 \
  --save-details

Base model:

cat > /tmp/lighteval_base_t06.yaml <<'EOF'
model_parameters:
  provider: "openai"
  model_name: "openai/Qwen/Qwen3.5-9B"
  base_url: "http://localhost:9002/v1"
  api_key: "dummy"
  generation_parameters:
    temperature: 0.6
    max_new_tokens: 1024
    top_p: 0.95
    top_k: 20
    min_p: 0.0
    presence_penalty: 0.0
    repetition_penalty: 1.0
EOF

lighteval endpoint litellm \
  /tmp/lighteval_base_t06.yaml \
  'lcb:codegeneration|0' \
  --output-dir /tmp/lcb_base_full_t06 \
  --save-details

Downloads last month: 11,617

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

6-bit

8-bit

Model tree for bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF

Base model

bigatuna/Qwen3.5-9b-Sushi-Coder

Adapter

bigatuna/Qwen3.5-9b-Sushi-Coder-RL

Quantized

(2)

this model

bigatuna
/

Qwen3.5-9b-Sushi-Coder-RL-GGUF