MLX 8-bit conversion of
IFM/K2-Horizon-7B
, a 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-7B checkpoint.
Release
Format
Quantization
Size
MLX safetensors (2 shards)
Affine 8-bit, group size 64
9.56 GB
The included
model.py
loader 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.
K2-Horizon-7B-MLX-8bit huggingface.co is an AI model on huggingface.co that provides K2-Horizon-7B-MLX-8bit's model effect (), which can be used instantly with this abenzerps K2-Horizon-7B-MLX-8bit model. huggingface.co supports a free trial of the K2-Horizon-7B-MLX-8bit model, and also provides paid use of the K2-Horizon-7B-MLX-8bit. Support call K2-Horizon-7B-MLX-8bit model through api, including Node.js, Python, http.
K2-Horizon-7B-MLX-8bit huggingface.co is an online trial and call api platform, which integrates K2-Horizon-7B-MLX-8bit's modeling effects, including api services, and provides a free online trial of K2-Horizon-7B-MLX-8bit, you can try K2-Horizon-7B-MLX-8bit online for free by clicking the link below.
abenzerps K2-Horizon-7B-MLX-8bit online free url in huggingface.co:
K2-Horizon-7B-MLX-8bit is an open source model from GitHub that offers a free installation service, and any user can find K2-Horizon-7B-MLX-8bit on GitHub to install. At the same time, huggingface.co provides the effect of K2-Horizon-7B-MLX-8bit install, users can directly use K2-Horizon-7B-MLX-8bit installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
K2-Horizon-7B-MLX-8bit install url in huggingface.co: