abenzerps/K2-Horizon-MoVA-36B-A4B-MLX-4bit
K2-Horizon-MoVA-36B-A4B MLX-4bit
MLX 4-bit conversion of IFM/K2-Horizon-MoVA-36B-A4B, a sparse Mixture-of-Experts model with Mixture-of-Values attention (MoVA), 36B total parameters, and approximately 4B active parameters per token. The source checkpoint supports a native context length of 524,288 tokens (512K).
Benchmarks
Benchmark results reported by IFM for the original K2-Horizon-MoVA-36B-A4B checkpoint.
Release
The MoE and MoVA router weights remain at 8-bit; other eligible weights use affine 4-bit quantization. This is a text-only release; no vision projector is required. The repository includes a source-compatible `chat_template.jinja`, the custom MLX model implementation required by this architecture, and `SHA256SUMS`.
Usage
pip install -U mlx-lm
mlx_lm.generate \
--model abenzerps/K2-Horizon-MoVA-36B-A4B-MLX-4bit \
--prompt "Explain why reproducible builds matter." \
--max-tokens 512 --temp 1.0 --top-p 0.95Use a current mlx-lm release. The source model supports 512K context; usable context length depends on available unified memory and KV-cache settings.
Source
- Model: IFM/K2-Horizon-MoVA-36B-A4B
- Source revision: `05cab0a`
- License: Apache-2.0
- Checksums: SHA256SUMS
