abenzerps/K2-Horizon-3.7B-MLX-8bit

abenzerps 已认证

🤗 Hugging Face 来源text-generationapache-2.05.1B 参数10 GBsafetensors✓ 4 个校验和今天更新

K2-Horizon-3.7B MLX — 8-bit

MLX 8-bit conversion of IFM/K2-Horizon-3.7B, a 3.7B dense decoder-only model for reasoning, coding, long-context work, and tool use. The source checkpoint supports a native context length of 524,288 tokens (512K).

Benchmarks

Benchmark results reported by IFM for the original IFM/K2-Horizon-3.7B checkpoint.

Release

Format	Quantization	Size
MLX safetensors	Affine 8-bit, group size 64	5.40 GB

The included k2_horizon_mlx.py adapter preserves K2 Horizon's grouped RMSNorm. Use it with MLX-LM and --trust-remote-code. The model is text-only; no vision projector or MTP files are included.

Usage

pip install -U mlx-lm
mlx_lm.generate \
  --model . \
  --trust-remote-code \
  --prompt "Explain why reproducible builds matter." \
  --max-tokens 512

Source

Model: IFM/K2-Horizon-3.7B
Source revision: 633f52a
License: Apache-2.0
Checksums: SHA256SUMS.txt