Instructions to use logic65/whittle-dev 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/whittle-dev 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/whittle-dev:Q8_0
# Run inference directly in the terminal:
llama cli -hf logic65/whittle-dev:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf logic65/whittle-dev:Q8_0
# Run inference directly in the terminal:
llama cli -hf logic65/whittle-dev: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/whittle-dev:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf logic65/whittle-dev: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/whittle-dev:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf logic65/whittle-dev:Q8_0

Use Docker

docker model run hf.co/logic65/whittle-dev:Q8_0

LM Studio
Jan
Ollama
How to use logic65/whittle-dev with Ollama:
```
ollama run hf.co/logic65/whittle-dev:Q8_0
```
Unsloth Desktop

How to use logic65/whittle-dev with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf logic65/whittle-dev: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/whittle-dev:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use logic65/whittle-dev with Docker Model Runner:
```
docker model run hf.co/logic65/whittle-dev:Q8_0
```

Lemonade

How to use logic65/whittle-dev with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull logic65/whittle-dev:Q8_0

Run and chat with the model

lemonade run user.whittle-dev-Q8_0

List all available models

lemonade list

Hermes Agent

How to use logic65/whittle-dev 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/whittle-dev: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/whittle-dev:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use logic65/whittle-dev with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf logic65/whittle-dev: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/whittle-dev: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-dev / README.md

logic65

Claude Opus 5.5

card: cleanup (structure, status line, support block, dated corrections; measured numbers unchanged)

f8ab13d verified 6 days ago

preview code

Raw History Blame Contribute Delete

3 kB

	---
	tags:
	- whittle
	- research
	- training-checkpoints
	---

	# whittle-dev

	> ### ☕ Support this work
	> Whittle is built by one person on a grocery budget and rented GPU hours. If this research is useful to you, or you want to see it finished:
	> [ko-fi.com/davida81328](https://ko-fi.com/davida81328). Every hour of GPU time goes straight into the next checkpoint, and every checkpoint, table and log lands in these repos.

	Nightly training checkpoints (trainer state: HC/PLE/LoRA/gates) for Whittle-Next runs on Colab.
	`colab1/latest.pt` is overwritten as the run progresses; `colab1/step<N>.pt` are milestones (the earlier
	note on this card said every 1000 steps; the tree holds `step200.pt` to `step4400.pt`, every 200 steps, as
	the Whittle-Next-27B-A3B card states). Load with the
	trainer (`RESUME_CKPT=`), not as a standalone model.

	## Status

	Development artefacts, not a release. These are the run directories referenced by the
	[Whittle-Next-27B-A3B](https://huggingface.co/logic65/Whittle-Next-27B-A3B) and
	[Whittle-Qwen-3.8-35B-A3B](https://huggingface.co/logic65/Whittle-Qwen-3.8-35B-A3B) cards: `colab1/` is the
	v4.4 run of Whittle-Next-27B-A3B (its checkpoints and run-end table), and `tbl1/`, `lw2/`, `lw5/` and
	`agentfix2/` are the checkpoints of the same names described on the Whittle-Qwen-3.8-35B-A3B card. The
	other directories (`colab2/`, `lw1/`, `lw3/`, `lw4/`, `agentfix/`, `ai2-archive/`) are runs of the same
	line that no card describes.

	## What is here

	- `colab1/` — `step<N>.pt` (22 milestones), `latest.pt`, `ngram_table_final.npy`.
	- `colab2/` — `step<N>.pt`, `latest.pt`, `ngram_table_final.npy`, `eval/` (CE curve, layer-wise eval logs and JSON, export log, `TRAIN.log`).
	- `lw1/` — `step<N>.pt`, `latest.pt`, `ngram_table_final.npy`, `eval/` (CE curve, layer-wise eval logs and JSON, export log, `TRAIN.log`).
	- `lw2/`, `lw3/`, `lw4/`, `lw5/` — `step<N>.pt`, `latest.pt`, `ngram_table.npy`, `ple_hash.json`, `TRAIN.log`, `eval/` (CE curve, layer-wise eval logs and JSON, `math60_replies.jsonl` + `math60_score.txt`, export/convert logs) and one Q8_0 GGUF per run: `Whittle-Qwen-3.8-35B-A3B-lw2-Q8_0.gguf`, `…-lw3-…`, `…-lw4-…`, `…-lw5-…`.
	- `tbl1/` — `step<N>.pt`, `latest.pt`, `ngram_table.npy`, `ple_hash.json`, `eval/` (GGUF build and quantisation logs, `gguf_sizes.json`).
	- `agentfix/` — `latest.pt`, `step200.pt`.
	- `agentfix2/` — `latest.pt`, `step300.pt`, `bf16/` (full weights, 14 safetensors shards + config, tokenizer and chat template) and `Whittle-Qwen-3.8-35B-A3B-agentfix2-Q8_0.gguf`.
	- `ai2-archive/` — archived trainer states: `reader7/`, `reader9/`, `reader11/`, `reader12/` (`TRAIN.log`, `ngram_table.npy`, `ple_hash.json`, and `keep_final.pt` for all but reader9), `v3ref/` (`resume_from.pt`, `ple_hash.json`), `v4/` (`colab_onpolicy_next_step42.pt`).

	The checkpoints are trainer state, not standalone models: the trainer, exporter and the frozen body they
	apply to are described on the two model cards above.