Instructions to use logic65/Qwen3.8-Whittle-tri-14.7B-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use logic65/Qwen3.8-Whittle-tri-14.7B-chat 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 logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0
# Run inference directly in the terminal:
llama cli -hf logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0
# Run inference directly in the terminal:
llama cli -hf logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0

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 logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0

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 logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0

Use Docker

docker model run hf.co/logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0

LM Studio
Jan
Ollama
How to use logic65/Qwen3.8-Whittle-tri-14.7B-chat with Ollama:
```
ollama run hf.co/logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0
```

Unsloth Studio

How to use logic65/Qwen3.8-Whittle-tri-14.7B-chat 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 logic65/Qwen3.8-Whittle-tri-14.7B-chat 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 logic65/Qwen3.8-Whittle-tri-14.7B-chat to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for logic65/Qwen3.8-Whittle-tri-14.7B-chat to start chatting

How to use logic65/Qwen3.8-Whittle-tri-14.7B-chat with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0

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": "logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use logic65/Qwen3.8-Whittle-tri-14.7B-chat with Docker Model Runner:
```
docker model run hf.co/logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0
```

Lemonade

How to use logic65/Qwen3.8-Whittle-tri-14.7B-chat with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0

Run and chat with the model

lemonade run user.Qwen3.8-Whittle-tri-14.7B-chat-Q8_0

List all available models

lemonade list

Hermes Agent

How to use logic65/Qwen3.8-Whittle-tri-14.7B-chat with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0

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 logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use logic65/Qwen3.8-Whittle-tri-14.7B-chat with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0

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 "logic65/Qwen3.8-Whittle-tri-14.7B-chat:Q8_0" \
  --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"

Whittle tri 14.7B chat (RESEARCH PREVIEW - REQUIRES FURTHER POST TRAINING)

A 14.7B compression of Qwen3.8-27B, repaired in two rounds so that it can hold a conversation. This is a research preview. It still needs further post training and its factual accuracy is weak. Published as an honest work in progress.

The problem

The compressed model kept its knowledge but could not talk: in open-ended chat it collapsed into repetition ("the fan fan fan..."), and asked for an iterative Fibonacci it wrote a broken recursive one. The cause was the training signal, not the weights. The original heal packed conversations into 256-token blocks and took the loss on every token, so predicting questions was rewarded as much as answering them.

Round 1 - instruction repair (SFT)

One conversation per sequence at 4096, never truncated mid-conversation, loss on assistant turns only. 4.58M tokens, 1.33 epochs, 90 minutes on one A100.

Round 2 - distillation from the parent (KD)

Top-64 logits cached from the Qwen3.8-27B parent, then a decoupled top-k objective: a binary KL matching the total probability mass the student places on the teacher's top-k set, plus a conditional KL matching the shape within that set, plus a CE anchor. Matching only the shape (the naive approach) leaves total set mass unconstrained, and the student drifts into over-confident, repetitive sampling. r=128, lr 5e-5, 55 min.

Measured, same prompts and sampler throughout

test	base	after SFT	after SFT+KD
4-gram repetition, 3-turn chat	0.55 / 0.58	0.38 / 0.39	0.04 / 0.10 / 0.01
instruction following (15 templated checks)	11/15	11/15	11/15
39-prompt battery (raw completions)	34/39	31/39	32/39
"Fibonacci, iteratively"	recursive, broken	correct	correct

KD recovered four raw-completion items that SFT had cost (add3, square, half, py_print) without bringing the looping back: SFT fixes conversation, KD pulls the distribution back toward the parent.

Known limitations

Factual accuracy is poor. It states wrong things confidently.
It sometimes returns an empty answer.
Needs further post training. This is a starting point, not a finished model.

Files

whittle-tri-sftkd-q8_0.gguf - recommended, final SFT+KD model, Q8_0, 15.6GB
whittle-tri-sft-q8_0.gguf - round 1 only, kept for comparison
bf16 safetensors in the repo root (round 1; final bf16 on request)

arch qwen35, EOS 248046. Serve with thinking off. Samplers: temp 0.7, top_p 0.8, top_k 20.

Funding

Self funded on personal hardware and paid Colab time. If this is useful, support keeps it going: ko-fi.com/davida81328

Downloads last month: 2,090

Safetensors

Model size

15B params

Tensor type

BF16

Inference Providers NEW

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

Model tree for logic65/Qwen3.8-Whittle-tri-14.7B-chat

Base model

Qwen/Qwen3.8-27B

Quantized

Qwen/Qwen3.8-27B-FP8

Quantized

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

Quantized

(1)

this model