Instructions to use EganAI/qwen3.5-9b-terminal-merge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EganAI/qwen3.5-9b-terminal-merge with Transformers:

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

pipe = pipeline("text-generation", model="EganAI/qwen3.5-9b-terminal-merge")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("EganAI/qwen3.5-9b-terminal-merge")
model = AutoModelForImageTextToText.from_pretrained("EganAI/qwen3.5-9b-terminal-merge")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use EganAI/qwen3.5-9b-terminal-merge with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="EganAI/qwen3.5-9b-terminal-merge",
	filename="qwen3.5-9b-terminal-merge-F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use EganAI/qwen3.5-9b-terminal-merge with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf EganAI/qwen3.5-9b-terminal-merge:F16
# Run inference directly in the terminal:
llama-cli -hf EganAI/qwen3.5-9b-terminal-merge:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf EganAI/qwen3.5-9b-terminal-merge:F16
# Run inference directly in the terminal:
llama-cli -hf EganAI/qwen3.5-9b-terminal-merge:F16

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 EganAI/qwen3.5-9b-terminal-merge:F16
# Run inference directly in the terminal:
./llama-cli -hf EganAI/qwen3.5-9b-terminal-merge:F16

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 EganAI/qwen3.5-9b-terminal-merge:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EganAI/qwen3.5-9b-terminal-merge:F16

Use Docker

docker model run hf.co/EganAI/qwen3.5-9b-terminal-merge:F16

LM Studio
Jan

vLLM

How to use EganAI/qwen3.5-9b-terminal-merge with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EganAI/qwen3.5-9b-terminal-merge"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EganAI/qwen3.5-9b-terminal-merge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EganAI/qwen3.5-9b-terminal-merge:F16

SGLang

How to use EganAI/qwen3.5-9b-terminal-merge 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 "EganAI/qwen3.5-9b-terminal-merge" \
    --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": "EganAI/qwen3.5-9b-terminal-merge",
		"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 "EganAI/qwen3.5-9b-terminal-merge" \
        --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": "EganAI/qwen3.5-9b-terminal-merge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use EganAI/qwen3.5-9b-terminal-merge with Ollama:
```
ollama run hf.co/EganAI/qwen3.5-9b-terminal-merge:F16
```

Unsloth Studio new

How to use EganAI/qwen3.5-9b-terminal-merge 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 EganAI/qwen3.5-9b-terminal-merge 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 EganAI/qwen3.5-9b-terminal-merge to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EganAI/qwen3.5-9b-terminal-merge to start chatting

Pi new

How to use EganAI/qwen3.5-9b-terminal-merge with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf EganAI/qwen3.5-9b-terminal-merge:F16

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": "EganAI/qwen3.5-9b-terminal-merge:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use EganAI/qwen3.5-9b-terminal-merge with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf EganAI/qwen3.5-9b-terminal-merge:F16

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 EganAI/qwen3.5-9b-terminal-merge:F16

Run Hermes

hermes

Docker Model Runner
How to use EganAI/qwen3.5-9b-terminal-merge with Docker Model Runner:
```
docker model run hf.co/EganAI/qwen3.5-9b-terminal-merge:F16
```

Lemonade

How to use EganAI/qwen3.5-9b-terminal-merge with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EganAI/qwen3.5-9b-terminal-merge:F16

Run and chat with the model

lemonade run user.qwen3.5-9b-terminal-merge-F16

List all available models

lemonade list

Qwen3.5-9B Terminal Merge

An experimental layer-wise merge of 16 Qwen3.5-9B variants aimed at terminal and CLI-style command generation.

Status Update

I need to correct the original benchmark claim on this repo.

The first version of this model card reported results from an earlier evaluation setup that I no longer trust. After rerunning the comparison on the current 60-task Modal Harbor benchmark on March 17, 2026, this v1 merge did not beat the current base Qwen/Qwen3.5-9B result.

I should not have presented the earlier result as a reliable improvement over base. Sorry about that.

For now, this repo should be treated as an experimental merge release rather than a confirmed upgrade over base Qwen.

Current Internal Benchmark Snapshot

Fresh 60-task Modal Harbor run:

Model	Tasks Passed	Pass Rate
Qwen/Qwen3.5-9B	53/60	88.3%
EganAI/qwen3.5-9b-terminal-merge	50/60	83.3%

The benchmark covers file operations, text processing, git workflows, networking, Python scripting, and system administration tasks in sandboxed execution environments.

Download

Format	Size	Link
Safetensors (bf16)	~18 GB	Download
GGUF F16	17.9 GB	Download
GGUF Q8_0	9.53 GB	Download

Model Details

Architecture: Qwen3.5 (hybrid linear + full attention)
Parameters: 9B total
Context Length: 262,144 tokens
Precision: bfloat16
Layers: 32 (8 full attention + 24 linear attention)
Merge Method: Layer-wise linear merge with optimized per-layer weights

Source Models

This model combines optimized layer-wise weights from 16 Qwen3.5-9B variants spanning reasoning, instruction-following, and general capability specializations:

Category	Models
Core	Qwen/Qwen3.5-9B, unsloth/Qwen3.5-9B
Abliterated	darkc0de/Qwen3.5-9B-heretic, lukey03/Qwen3.5-9B-abliterated, llmfan46/Qwen3.5-9B-ultimate-irrefusable-heretic, llmfan46/Qwen3.5-9B-ultra-heretic, jwest33/qwen3.5-9b-null-space-abliterated, trohrbaugh/Qwen3.5-9B-heretic-v2, osirisbrain/OsirisCortex-v6
Reasoning	DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-THINKING, DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT, crownelius/Crow-9B-Opus-4.6-Distill-Heretic_Qwen3.5
Specialized	alecccdd/Qwen3.5-9B-paraphrasing-orpo, lugman-madhiai/Qwen3.5-9B-MHS-Interleaved, Hastagaras/Qwen3.5-9B-GLM-Wannabe, zenlm/zen4

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "EganAI/qwen3.5-9b-terminal-merge"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="bfloat16",
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Find all Python files larger than 1MB and sort by size descending"}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

GGUF (llama.cpp)

# Download Q8_0 (recommended balance of quality/size)
wget https://huggingface.co/EganAI/qwen3.5-9b-terminal-merge/resolve/main/qwen3.5-9b-terminal-merge-q8_0.gguf

# Run with llama.cpp
./llama-cli -m qwen3.5-9b-terminal-merge-q8_0.gguf \
  -p "Find all files modified in the last 24 hours and sort by size:" \
  -n 512 --temp 0.7

GGUF (Python)

from huggingface_hub import hf_hub_download
from llama_cpp import Llama

model_path = hf_hub_download(
    repo_id="EganAI/qwen3.5-9b-terminal-merge",
    filename="qwen3.5-9b-terminal-merge-q8_0.gguf",
)

llm = Llama(model_path=model_path, n_ctx=4096, n_gpu_layers=-1)

output = llm(
    "List all running Docker containers and their memory usage:",
    max_tokens=256,
    temperature=0.7,
)
print(output["choices"][0]["text"])

vLLM Serving

vllm serve EganAI/qwen3.5-9b-terminal-merge \
    --language-model-only \
    --dtype bfloat16 \
    --max-model-len 8192

Note: Use --language-model-only since this is a multimodal architecture served for text-only inference.

Training Details

The per-layer merge weights were optimized by evaluating candidates on a suite of 60 terminal tasks using vLLM inference in sandboxed environments. The optimization searched across layer-group weight distributions to find a strong blend of the 16 source models.

That earlier optimization run produced a candidate worth publishing as an experiment, but the original benchmark comparison against base should be considered superseded by the newer reevaluation above.

Limitations

This v1 release does not currently show a verified win over base Qwen/Qwen3.5-9B on my latest internal benchmark run
Optimized specifically for terminal/CLI tasks; general-purpose performance may vary
Requires --language-model-only flag when serving with vLLM due to multimodal architecture
Visual capabilities are inherited from the base model but were not part of the optimization target