Modelpublic

hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-8bit

sourceHugging Faceapache-2.0updated 22d agoView on Hugging Face

1likes394downloads

Model Card

K2-Horizon-MoVA-36B-A4B MLX-8bit

8-bit uniform quantization conversion of 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 by the IFM Team, released under Apache-2.0.

Conversion: Quantized to MLX format using Hermes Agent 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-8bit   --prompt "Explain why long-context evaluation is difficult."   --max-tokens 512 --temp 1.0 --top-p 0.95

Reasoning

K2-Horizon is a reasoning model. Always use reasoning_effort="high" for best results:

python

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
response = client.chat.completions.create(
    model="hermitdave/K2-Horizon-MoVA-36B-A4B-MLX-8bit",
    messages=[{"role": "user", "content": "Explain quantum entanglement."}],
    extra_body={"chat_template_kwargs": {"reasoning_effort": "high"}},
)
print("Reasoning:", getattr(response.choices[0].message, "reasoning_content", None))
print("Answer:", response.choices[0].message.content)

Benchmark Results

Benchmark	K2-Horizon-MoVA-36B-A4B
tau3-Banking (Agentic tool use)	26.8
Terminal-Bench 2.1 (Agentic terminal use)	58.6
GPQA Diamond (Graduate-level science QA)	80.8
AA-LCR (Long-context reasoning)	66.3

Scores in %. See model card for full results.

oMLX Patch

K2-Horizon requires oMLX v0.6.4+ with the K2-Horizon support patch (PR #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

@misc{k2horizon2026,
  title  = {Introducing K2 Horizon: Frontier Performance, Radically Open},
  author = {{IFM Team}},
  year   = {2026},
  url    = {https://ifm.ai/blog/k2/},
}

License

Apache-2.0 (same as upstream).