Instructions to use Piecrust/Spike-2B-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Piecrust/Spike-2B-MLX with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Piecrust/Spike-2B-MLX")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use Piecrust/Spike-2B-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Piecrust/Spike-2B-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Piecrust/Spike-2B-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Piecrust/Spike-2B-MLX with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Piecrust/Spike-2B-MLX"

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-2B-MLX

Run Hermes

hermes

OpenClaw new

How to use Piecrust/Spike-2B-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Piecrust/Spike-2B-MLX"

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-2B-MLX" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use Piecrust/Spike-2B-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Piecrust/Spike-2B-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Piecrust/Spike-2B-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Piecrust/Spike-2B-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Spike-2B · MLX (4-bit)

Spike is the on-device assistant in the Spike AI iOS app. This is the build that runs on your iPhone — 4-bit MLX, served via mlx-swift. 📱 Get it on the App Store: https://apps.apple.com/app/spike-ai/id6749781844

A LoRA fine-tune of Qwen/Qwen3.5-2B (a vision-language model), specialized for Spike's on-device tool-calling — reminders, calendar, Apple Home, maps, web, files, code, and the SSH/agent toolset — plus vision (read a flyer → create the event, a note → a reminder, a receipt → the total). English and German. It emits Spike's text tool grammar:

tool:<name> {"key":"value"}

Files

4-bit MLX weights (model.safetensors, ~1.7 GB total) + tokenizer, processor, and chat template. Load with mlx-swift / mlx-vlm on Apple silicon.

Qwen3.5 is a new hybrid (linear-attention + full-attention) architecture. It runs in the Spike app's mlx-swift runtime (which implements qwen3_5); a text-only GGUF build is also available for llama.cpp servers.

Eval — Spike harness (before → after)

Metric	Base Qwen3.5-2B	Spike-2B
Tool calls (thinking off)	39.8%	99.6%
Tool calls (thinking on)	—	96.8%
Vision (image → tool / answer)	67.5%	100%
Valid JSON on tool calls	~64%	100%
Normal-chat tool-leak (lower=better)	—	0%

Trained in three stages — text + thinking + general + German (~22.5k samples), an 800-image vision-replay stage, then a conversation-repair stage (distilled base-model chat + contrastive tool/vision replay) — so the model keeps its enable_thinking reasoning and vision, speaks Spike's tool grammar, and does not hijack casual chat into tool calls (normal-chat tool-leak 0%).

Usage notes

Trained on Spike's compact system prompt; use that exact prompt for best results.
Supports optional reasoning via the enable_thinking chat-template kwarg.
Vision: pass an image with the user turn; the model reads it and answers or calls a tool.
Tool calls are plain text tool:<name> {json} — one per turn.

License

Derivative of Qwen3.5-2B under the Apache 2.0 License.

Downloads last month: 76

Safetensors

Model size

0.6B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for Piecrust/Spike-2B-MLX

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Quantized

(141)

this model