Instructions to use hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit 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("hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit")

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 hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit 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 "hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit"

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 hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit"

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 "hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit" \
  --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"

hermitdave commited on 3 days ago

Commit

00748b4

verified ·

1 Parent(s): 2d8ca73

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +28 -17

README.md CHANGED Viewed

@@ -4,36 +4,24 @@ tags:
   - mlx
   - apple-silicon
   - text-generation
-  - 6-bit
 license: apache-2.0
 ---
-# K2-Horizon-MoVA-36B-A4B MLX
 **Upstream model:** [IFM/K2-Horizon-MoVA-36B-A4B](https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B) by the IFM Team, released under Apache-2.0.
 **Conversion:** Quantized to MLX format using [Hermes Agent](https://hermes-agent.nousresearch.com) with `mlx-lm` and `oMLX`.
-MLX conversions of [IFM/K2-Horizon-MoVA-36B-A4B](https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B), a sparse Mixture-of-Experts model with Mixture-of-Values attention (36B total / 4B active parameters).
-## Available Formats
-| Format | Size | Quality | Use Case |
-|--------|------|---------|----------|
-| **oQ4e** | ~21 GB | ~uniform 6-bit quality | Best quality-per-GB |
-| **6-bit** | ~28 GB | High | Quality-focused, fits 40+ GB |
-| **8-bit** | ~40 GB | Near-lossless | Reference quality, 64 GB+ |
 ## Quickstart
 ```bash
 pip install -U mlx-lm
-# Generate
-python3 -m mlx_lm.generate \
-  --model hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit \
-  --prompt "Explain why long-context evaluation is difficult." \
-  --max-tokens 512 --temp 1.0 --top-p 0.95
 ```
 ## Reasoning
@@ -64,6 +52,29 @@ print("Answer:", response.choices[0].message.content)
 Scores in %. See [model card](https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B) for full results.
 ## Citation
 ```bibtex

   - mlx
   - apple-silicon
   - text-generation
+  - oQ
 license: apache-2.0
 ---
+# K2-Horizon-MoVA-36B-A4B MLX-6bit
+6-bit uniform quantization conversion of [IFM/K2-Horizon-MoVA-36B-A4B](https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B), a sparse Mixture-of-Experts model with Mixture-of-Values attention (36B total / 4B active parameters, 512K context).
 **Upstream model:** [IFM/K2-Horizon-MoVA-36B-A4B](https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B) by the IFM Team, released under Apache-2.0.
 **Conversion:** Quantized to MLX format using [Hermes Agent](https://hermes-agent.nousresearch.com) with `mlx-lm` and `oMLX`.
 ## Quickstart
 ```bash
 pip install -U mlx-lm
+python3 -m mlx_lm.generate   --model hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-6bit   --prompt "Explain why long-context evaluation is difficult."   --max-tokens 512 --temp 1.0 --top-p 0.95
 ```
 ## Reasoning
 Scores in %. See [model card](https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B) for full results.
+## oMLX Patch
+K2-Horizon requires oMLX v0.6.4+ with the [K2-Horizon support patch (PR #3441)](https://github.com/jundot/omlx/pull/3441). This patch adds:
+- `k2_horizon` model type support
+- Reasoning content handling (`<ifm|think>` tags)
+- Tool call parsing (plain text and XML formats)
+- Multi-turn conversation support
+Without this patch, oMLX will refuse to load K2-Horizon models with `ValueError: Model type k2_horizon not supported`.
+## Chat Template
+K2-Horizon uses IFM's custom chat template with reasoning and tool calling support. Key tags:
+| Tag | Purpose |
+|-----|---------|
+| `<ifm\|think>`, `<ifm\|think_fast>`, `<ifm\|think_faster>` | Thinking blocks |
+| `<\|ifm\|im_start|>`, `<\|ifm\|im_end\|>` | Message delimiters |
+| `<ifm\|tool_call>`, `<ifm\|arg_key>`, `<ifm\|arg_value>` | Tool call structure |
+All tags are automatically stripped by oMLX before responses reach users.
 ## Citation
 ```bibtex