Instructions to use kuzaai/kuza-qwen-3.5-4b-quant-study with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use kuzaai/kuza-qwen-3.5-4b-quant-study 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 kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kuzaai/kuza-qwen-3.5-4b-quant-study: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 kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kuzaai/kuza-qwen-3.5-4b-quant-study: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 kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M

Use Docker

docker model run hf.co/kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M

LM Studio
Jan
Ollama
How to use kuzaai/kuza-qwen-3.5-4b-quant-study with Ollama:
```
ollama run hf.co/kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M
```
Unsloth Desktop

How to use kuzaai/kuza-qwen-3.5-4b-quant-study with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kuzaai/kuza-qwen-3.5-4b-quant-study: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": "kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kuzaai/kuza-qwen-3.5-4b-quant-study with Docker Model Runner:
```
docker model run hf.co/kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M
```

Lemonade

How to use kuzaai/kuza-qwen-3.5-4b-quant-study with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M

Run and chat with the model

lemonade run user.kuza-qwen-3.5-4b-quant-study-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use kuzaai/kuza-qwen-3.5-4b-quant-study with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kuzaai/kuza-qwen-3.5-4b-quant-study: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 kuzaai/kuza-qwen-3.5-4b-quant-study:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kuzaai/kuza-qwen-3.5-4b-quant-study with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kuzaai/kuza-qwen-3.5-4b-quant-study: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 "kuzaai/kuza-qwen-3.5-4b-quant-study: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"

Kuza Qwen 3.5-4B Quant Study

Quantization vs finetuning diagnosis for the Kuza East Africa agricultural assistant. Source weights and past quants from kuzaai/kuza-qwen-3.5-4b.

Diagnosis

Verdict: finetuning_or_template_issue
BF16 hidden_mean: 0.479
Screen winner: iq3_xs_imatrix_ssm
BF16 hidden_mean=0.479 is below threshold 0.75; quantization is unlikely the root cause.

Layout

artifacts/ — downloaded reference GGUF, imatrix, tokenizer, past quants
quants/ — newly quantized GGUF candidates from this study
screen/ — KLD logs, hidden-set reports, bench logs, results.json
results/ — baseline eval, report/analysis.md, per-model JSON
upload_manifest.json — path, size, sha256 for every uploaded file

Past-run quants (re-evaluated)

q4_k_m_imatrix — q4_k_m (from kuzaai/kuza-qwen-3.5-4b)
q4_k_xl_ssm — q4_k_m (from kuzaai/kuza-qwen-3.5-4b)
q4_k_s_ssm — q4_k_s (from kuzaai/kuza-qwen-3.5-4b)

New quant candidates

q4_k_m_plain — q4_k_m — Community-style imatrix Q4_K_M without tensor overrides.
q5_k_m_imatrix_ssm — q5_k_m — Quality step-up per Hob-forge Qwen3.5-4B benchmarks.
q3_k_m_imatrix_ssm — q3_k_m — User-requested 3-bit K-quant with SSM/attention protection.
iq3_xs_imatrix_ssm — iq3_xs — User-requested 3-bit I-quant; may trade speed for size.
iq4_xs_imatrix_ssm — iq4_xs — Smallest 4-bit I-quant with hybrid SSM protection.
q6_k_imatrix — q6_k — Near-lossless quant reference.

Download

huggingface-cli download kuzaai/kuza-qwen-3.5-4b-quant-study --local-dir ./qwen-quant-study

Primary metric: hidden-set rubric score on 36 EN/SW agriculture prompts (data/hidden_prompts.jsonl in the source repo). Ranking: hidden_mean desc, then GGUF size asc, then GPU generation TPS desc.