Instructions to use Piecrust/Spike-350M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Piecrust/Spike-350M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Piecrust/Spike-350M-GGUF",
	filename="Spike-350M-F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Piecrust/Spike-350M-GGUF 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 Piecrust/Spike-350M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Piecrust/Spike-350M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Piecrust/Spike-350M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Piecrust/Spike-350M-GGUF: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 Piecrust/Spike-350M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Piecrust/Spike-350M-GGUF: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 Piecrust/Spike-350M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Piecrust/Spike-350M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Piecrust/Spike-350M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Piecrust/Spike-350M-GGUF with Ollama:
```
ollama run hf.co/Piecrust/Spike-350M-GGUF:Q4_K_M
```

Unsloth Studio

How to use Piecrust/Spike-350M-GGUF 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 Piecrust/Spike-350M-GGUF 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 Piecrust/Spike-350M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Piecrust/Spike-350M-GGUF to start chatting

How to use Piecrust/Spike-350M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Piecrust/Spike-350M-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Piecrust/Spike-350M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Piecrust/Spike-350M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Piecrust/Spike-350M-GGUF: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 Piecrust/Spike-350M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Piecrust/Spike-350M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Piecrust/Spike-350M-GGUF: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 "Piecrust/Spike-350M-GGUF: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"

Docker Model Runner
How to use Piecrust/Spike-350M-GGUF with Docker Model Runner:
```
docker model run hf.co/Piecrust/Spike-350M-GGUF:Q4_K_M
```

Lemonade

How to use Piecrust/Spike-350M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Piecrust/Spike-350M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Spike-350M-GGUF-Q4_K_M

List all available models

lemonade list

Spike-350M

Spike is the in-browser assistant of Pieswap, the DEX on the Dusk network. This model is a LoRA fine-tune of LiquidAI/LFM2.5-350M, specialized for Spike's tool-calling workload: swaps, wrapping, staking, liquidity management, balances, pools, and app settings — in English, German, and Dutch. It runs fully client-side via wllama (llama.cpp WebAssembly).

Files

File	Use
`Spike-350M-Q5_K_M.gguf` (260 MB)	Production quant on desktop (pieswap.app)
`Spike-350M-Q4_K_S.gguf` (221 MB)	Production quant on mobile — smaller download, faster CPU prompt processing
`Spike-350M-Q4_K_M.gguf` (229 MB)	Alternative quant
`Spike-350M-F16.gguf` (709 MB)	Full-precision source for requantizing

pieswap.app serves Q5_K_M to desktop browsers and Q4_K_S to mobile devices: mobile runs on CPU, where Q4_K_S processes the prompt about 1.7x faster and downloads 15% less, at a negligible accuracy cost (see below).

Eval — v8 (Pieswap Spike harness, 354 cases)

Model	Score
LFM2.5-350M base (bf16, thinking off)	~50% on the original core set
Spike-350M v7 (Q5_K_M, in-browser)	221/224 on the previous 224-case harness
Spike-350M v8 (bf16, merged)	354/354 (100%)
Spike-350M v8 (Q5_K_M, in-browser via wllama)	354/354 (100%) — under BOTH seeds 42 and 1337, zero flaky
Spike-350M v8 (Q4_K_S, in-browser via wllama)	353/354 — dual-seed; single miss is one out-of-distribution slang phrasing (a settings read routed to wallet-status)

The v8 harness grew from 224 to 354 held-out cases and now also covers: prompt injection embedded in tool results (the model answers the user's original question and ignores the smuggled instruction), send-to-address scams (Pieswap has no transfer tool — the model says so instead of hallucinating a call), disconnected-wallet gating incl. retry-after-refusal, native-DUSK payout on liquidity removal (receiveNative), slippage percent→bps conversion, fraction arithmetic chains ("a third of my dusk" — balance read → exactly computed amount), spelled-out amounts ("one and a half dusk"), price reads via pool ratio, creative slang for every tool, and German/Dutch across the full surface.

Trained on a ~14.9k-sample instruction dataset spanning distinct user registers (terse/sloppy-typist, verbose, percentage flows, deep liquidity management, wallet-gating contrastive pairs, German, Dutch, creative slang, adversarial/injection, clarification and error recovery, multi-turn context), extended with targeted sections addressing specific eval misses. LoRA r=64 all-linear on bf16, 2 epochs, completion-only loss, byte-identical to the production chat template and message shapes (tool results re-fed as user messages, assistant tool-call turns dropped).

Usage notes

The LFM2.5 base family supports optional reasoning via the enable_thinking chat-template kwarg. This fine-tune was trained entirely with thinking disabled — run it with enable_thinking: false. Thinking-on still works mechanically but is off-distribution for these weights (untrained thinking traces, untested tool accuracy, extra latency).
Tool calls are emitted in LFM2.5's native format: <|tool_call_start|>[execute_swap(tokenIn="DUSK", tokenOut="PIE", amountIn="10")]<|tool_call_end|> — llama.cpp parses these into OpenAI-style tool calls when tools are passed.
The system prompt must carry the Pieswap wallet-status line (Wallet status: connected (…) / Wallet status: not connected.) — the wallet-gating behavior is conditioned on it.
The model is a narrow specialist for the Pieswap tool schema and system prompt; it is not a general assistant.

License

Derivative of LFM2.5-350M under the LFM Open License v1.0.

Downloads last month: 451

GGUF

Model size

0.4B params

Architecture

lfm2

Hardware compatibility

4-bit

5-bit

16-bit

Inference Providers NEW

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

Model tree for Piecrust/Spike-350M-GGUF

Base model

LiquidAI/LFM2.5-350M-Base

Finetuned

LiquidAI/LFM2.5-350M

Quantized

(46)

this model