# IFM/K2-Horizon-MoVA-36B-A4B — vLLM serving recipe

> Sparse MoVA and MoE long-context model for research and production-style serving experiments

Configuration: hardware `h200` (8× H200) · strategy `single_node_tep` (Tensor + Expert Parallel) · variant `default` (BF16) · features `reasoning`, `tool_calling`

- Interactive page: https://recipes.vllm.ai/IFM/K2-Horizon-MoVA-36B-A4B
- This configuration as JSON: https://recipes.vllm.ai/IFM/K2-Horizon-MoVA-36B-A4B.json?hardware=h200

The commands below were rendered for exactly this configuration and take precedence over any example in the guide.

## Other configurations

Change the query string (the same parameters as the page URL) and fetch this URL again. Unknown or incompatible values fall back to the recipe default, so check the Configuration line.

- `hardware`: `h100`, `h200`, `b200`, `gb200`, `b300`, `gb300`, `mi300x`, `mi325x`, `mi350x`, `mi355x`
- `variant`: `default`
- `strategy`: `single_node_tep`, `multi_node_tep`, `multi_node_tp_pp` (multi-node strategies also need `nodes=<n>`)
- `features`: comma-separated list of `reasoning`, `tool_calling` (default: `reasoning`, `tool_calling`)

## Install

```bash
uv venv
source .venv/bin/activate
uv pip install -U vllm --torch-backend auto
```

Docker image: `vllm/vllm-openai:latest`

## Serve

```bash
vllm serve IFM/K2-Horizon-MoVA-36B-A4B \
  --trust-remote-code \
  --chat-template-content-format string \
  --dtype bfloat16 \
  --enable-expert-parallel \
  --tensor-parallel-size 8 \
  --reasoning-parser k2_horizon \
  --enable-auto-tool-choice \
  --tool-call-parser k2_horizon
```

Docker equivalent:

```bash
docker run --gpus all \
  --privileged --ipc=host -p 8000:8000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  vllm/vllm-openai:latest IFM/K2-Horizon-MoVA-36B-A4B \
  --trust-remote-code \
  --chat-template-content-format string \
  --dtype bfloat16 \
  --enable-expert-parallel \
  --tensor-parallel-size 8 \
  --reasoning-parser k2_horizon \
  --enable-auto-tool-choice \
  --tool-call-parser k2_horizon
```

## Guide

> Background reference. Commands in it are examples and may target another configuration — use the Serve section above.

### Overview

K2-Horizon-MoVA-36B-A4B is a mixture-of-expert (MoE) model in the IFM K2-Horizon
family. It combines MoVA attention and MoE layers, with 37.44B stored parameters
including embeddings, 5.95B active parameters per token, and support for up
to 524,288 tokens of context.

K2-Horizon is an open-weight IFM model family built for transparent
foundation-model research, staged checkpoint analysis, and practical
deployment. The series spans compact dense models for local experimentation,
dense mid-size and large models for high-quality research workloads, and
mixture-of-expert (MoE) models such as K2-Horizon-MoVA-36B-A4B for higher-capacity
serving.

### Launch Commands

```bash
vllm serve IFM/K2-Horizon-MoVA-36B-A4B \
  --tensor-parallel-size 2 \
  --trust-remote-code \
  --chat-template-content-format string \
  --dtype bfloat16 \
  --enable-expert-parallel \
  --reasoning-parser k2_horizon \
  --enable-auto-tool-choice \
  --tool-call-parser k2_horizon
```

### Client usage

```python
from openai import OpenAI

client = OpenAI(
    api_key="EMPTY", base_url="http://localhost:8000/v1", timeout=3600
)

resp = client.chat.completions.create(
    model="IFM/K2-Horizon-MoVA-36B-A4B",
    messages=[{"role": "user", "content": "Give me three primes above 100."}],
    temperature=1.0, top_p=0.95, max_tokens=2048,
)
print(resp.choices[0].message.content)
```

#### Thinking modes

The model supports selectable thinking through `chat_template_kwargs`, per
request or server-wide via `--default-chat-template-kwargs`:

- `{"reasoning_effort": "high"}` — full thinking (default).
- `{"reasoning_effort": "medium"}` — faster thinking.
- `{"reasoning_effort": "low"}` — fastest thinking.

### References

- [IFM/K2-Horizon-MoVA-36B-A4B on Hugging Face](https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B)
- [K2 Horizon Collection](https://huggingface.co/collections/IFM/k2-horizon)