Instructions to use anjadhe/anjadhe-qwen3.5-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use anjadhe/anjadhe-qwen3.5-4b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf anjadhe/anjadhe-qwen3.5-4b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf anjadhe/anjadhe-qwen3.5-4b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf anjadhe/anjadhe-qwen3.5-4b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf anjadhe/anjadhe-qwen3.5-4b: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 anjadhe/anjadhe-qwen3.5-4b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf anjadhe/anjadhe-qwen3.5-4b: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 anjadhe/anjadhe-qwen3.5-4b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf anjadhe/anjadhe-qwen3.5-4b:Q4_K_M

Use Docker

docker model run hf.co/anjadhe/anjadhe-qwen3.5-4b:Q4_K_M

LM Studio
Jan
Ollama
How to use anjadhe/anjadhe-qwen3.5-4b with Ollama:
```
ollama run hf.co/anjadhe/anjadhe-qwen3.5-4b:Q4_K_M
```
Unsloth Desktop

How to use anjadhe/anjadhe-qwen3.5-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf anjadhe/anjadhe-qwen3.5-4b:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "anjadhe/anjadhe-qwen3.5-4b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use anjadhe/anjadhe-qwen3.5-4b with Docker Model Runner:
```
docker model run hf.co/anjadhe/anjadhe-qwen3.5-4b:Q4_K_M
```

Lemonade

How to use anjadhe/anjadhe-qwen3.5-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull anjadhe/anjadhe-qwen3.5-4b:Q4_K_M

Run and chat with the model

lemonade run user.anjadhe-qwen3.5-4b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use anjadhe/anjadhe-qwen3.5-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf anjadhe/anjadhe-qwen3.5-4b: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 anjadhe/anjadhe-qwen3.5-4b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use anjadhe/anjadhe-qwen3.5-4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf anjadhe/anjadhe-qwen3.5-4b:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "anjadhe/anjadhe-qwen3.5-4b:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Anjadhe 4B (Qwen3.5-4B fine-tune)

The default local model for the Anjadhe personal AI app on Macs with 8–16 GB of memory. A LoRA fine-tune of Qwen/Qwen3.5-4B (Apache 2.0), tuned for the specific jobs Anjadhe runs all day on a small machine: reading email into structured insights, tool-calling against the app's task/goal/schedule/notes APIs, and answering questions about the user's own data — grounded, dated, and honest about what it can't find.

What's in the training data — and what isn't

Every training sample is synthetic. Emails come from seeded template generators; assistant conversations come from a scenario harness driving the real app against seeded demo data, with a larger open-weight model (Qwen3.6-35B-A3B) as the teacher. Labels were rejection-sampled hard: schema violations, invented dates (any date not literally present in the source), inconsistent action items, and unverified outcomes were dropped, never repaired. No user data of any kind was used. Prompt-injection attempts (instructions embedded in email bodies) are deliberately included with correct refusals, because a model that reads email is a model that reads attacker text.

Evaluations

Scored at temperature 0 through llama.cpp on the quantized artifact — the exact form that ships. Baselines are the untuned base at the same quant.

gate	stock Qwen3.5-4B	this model (v2)
Anjadhe insight eval v1 (17 regression fixtures)	17/17	17/17
Anjadhe insight eval v2 (11 boundary fixtures)	8/11	11/11
Agent tool-calling journeys (8)	7/8	7/8
Task-filing floor check	3/3	3/3
General-ability probe (det / judged)	9/14 · 12/12	11/14 · 12/12
Held-out agent scenarios (60 unseen, outcome-verified through the real app)	20/60	24/60

Intended use and limitations

Built to be good at Anjadhe's jobs at 4B size and speed — not a general-purpose replacement for larger models. Long, complex structured generations and deep open-ended reasoning remain better served by larger local models or hosted options, which Anjadhe offers as explicit opt-ins. The tune is coupled to Anjadhe's production prompts; it should behave like a normal Qwen3.5-4B on generic chat, but its improvements concentrate on Anjadhe-shaped inputs.

Files

anjadhe-qwen3.5-4b-*-Q4_K_M.gguf — the shipping quantization (~2.6 GB)

Training pipeline (generators, teacher labeling, verification harness, training scripts) is documented in the Anjadhe project repos.

Downloads last month: 3

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for anjadhe/anjadhe-qwen3.5-4b

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(394)

this model