Instructions to use scima/whittle-14.7b-scima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use scima/whittle-14.7b-scima 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 scima/whittle-14.7b-scima:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf scima/whittle-14.7b-scima:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf scima/whittle-14.7b-scima:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf scima/whittle-14.7b-scima: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 scima/whittle-14.7b-scima:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf scima/whittle-14.7b-scima: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 scima/whittle-14.7b-scima:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf scima/whittle-14.7b-scima:Q4_K_M

Use Docker

docker model run hf.co/scima/whittle-14.7b-scima:Q4_K_M

LM Studio
Jan
Ollama
How to use scima/whittle-14.7b-scima with Ollama:
```
ollama run hf.co/scima/whittle-14.7b-scima:Q4_K_M
```
Unsloth Desktop

How to use scima/whittle-14.7b-scima with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf scima/whittle-14.7b-scima: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": "scima/whittle-14.7b-scima:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use scima/whittle-14.7b-scima with Docker Model Runner:
```
docker model run hf.co/scima/whittle-14.7b-scima:Q4_K_M
```

Lemonade

How to use scima/whittle-14.7b-scima with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull scima/whittle-14.7b-scima:Q4_K_M

Run and chat with the model

lemonade run user.whittle-14.7b-scima-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use scima/whittle-14.7b-scima with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf scima/whittle-14.7b-scima: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 scima/whittle-14.7b-scima:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use scima/whittle-14.7b-scima with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf scima/whittle-14.7b-scima: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 "scima/whittle-14.7b-scima: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"

oh i didn't realise https://huggingface.co/logic65/Qwen3.8-Whittle-tri-14.7B-chat existed im gonna rerun the training with that instead

WHITTLE 14.7B MATHEMATICS SFT

yeah its better at maths (marginally) and kinda worse at general conversation so make of that what you will

32.4% gsm8k

34/39 battery made by logic65

===== LOOP TEST RESULTS ===== (q5_k_s)

single 12x3 24/36 ( 67%) loopy 23 short 1 err 0 medw 176

struct 6x3 10/18 ( 56%) loopy 8 short 3 err 0 medw 138

multi all 10/28 ( 36%) loopy 5 short 5 err 0 medw 118

late >=5th 3/12 ( 25%) loopy 1 short 2 err 0 medw 106

wouldn't recommend using in its current state

Downloads last month: -

GGUF

Model size

15B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Inference Providers NEW

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

Model tree for scima/whittle-14.7b-scima

Base model

Qwen/Qwen3.8-27B

Quantized

Qwen/Qwen3.8-27B-FP8

Quantized

logic65/Qwen3.8-Whittle-tri-14.7B

Quantized

(4)

this model