LLM EXPLORER 58,608 MODELS INDEXED

Kimi K2.7 Code 4bit by mlx-community

By mlx-community · 3382 downloads
HF Repo ↗ Copy URL

Kimi K2.7 Code 4bit is an open-source language model by mlx-community. Features: 1026.4b LLM, VRAM: 142.3GB, Quantized, LLM Explorer Score: 0.3.

  4-bit   4bit   Conversational   Custom code   En   Kimi k25   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Kimi-K2.7-Code-4bit 

Kimi K2.7 Code 4bit Parameters and Internals

LLM NameKimi K2.7 Code 4bit
Repository 🤗https://huggingface.co/mlx-community/Kimi-K2.7-Code-4bit 
Model Size1026.4b
Required VRAM142.3 GB
Updated2026-08-05
Maintainermlx-community
Model Typekimi_k25
Model Files  4.5 GB: 1-of-180   3.5 GB: 2-of-180   3.6 GB: 3-of-180   3.5 GB: 4-of-180   3.5 GB: 5-of-180   3.6 GB: 6-of-180   3.5 GB: 7-of-180   3.5 GB: 8-of-180   3.6 GB: 9-of-180   3.5 GB: 10-of-180   3.5 GB: 11-of-180   3.6 GB: 12-of-180   3.5 GB: 13-of-180   3.5 GB: 14-of-180   3.6 GB: 15-of-180   3.5 GB: 16-of-180   3.5 GB: 17-of-180   3.6 GB: 18-of-180   3.5 GB: 19-of-180   3.5 GB: 20-of-180   3.6 GB: 21-of-180   3.5 GB: 22-of-180   3.5 GB: 23-of-180   3.6 GB: 24-of-180   3.5 GB: 25-of-180   3.5 GB: 26-of-180   3.6 GB: 27-of-180   3.5 GB: 28-of-180   3.5 GB: 29-of-180   3.6 GB: 30-of-180   3.5 GB: 31-of-180   3.5 GB: 32-of-180   3.6 GB: 33-of-180   3.5 GB: 34-of-180   3.5 GB: 35-of-180   3.6 GB: 36-of-180   3.5 GB: 37-of-180   3.5 GB: 38-of-180   3.6 GB: 39-of-180   3.5 GB: 40-of-180
Supported Languagesen
Quantization Type4bit
Model ArchitectureKimiK25ForConditionalGeneration

Best Alternatives to Kimi K2.7 Code 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Kimi K2.7 Code Mlx DQ3 K M Q80K / 186 GB38655
Kimi K2.6 Mlx DQ3 K M Q80K / 186 GB61579
Kimi K2.5 Mlx DQ3 K M Q80K / 186 GB4433
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Kimi-K2.7-Code-4bit.