LLM EXPLORER 59,420 MODELS INDEXED

Kimi Dev 72B 8bit by mlx-community

By mlx-community · 361 downloads
HF Repo ↗ Copy URL

Kimi Dev 72B 8bit is an open-source language model by mlx-community. Features: 72b LLM, VRAM: 77.1GB, Context: 128K, License: mit, Quantized, LLM Explorer Score: 0.2.

  8-bit   8bit Base model:moonshotai/kimi-dev... Base model:quantized:moonshota...   Code   Conversational   Issue-resolving   Mlx   Quantized   Qwen2   Region:us   Safetensors   Sharded   Software   Swebench   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Kimi-Dev-72B-8bit 

Kimi Dev 72B 8bit Parameters and Internals

LLM NameKimi Dev 72B 8bit
Repository 🤗https://huggingface.co/mlx-community/Kimi-Dev-72B-8bit 
Base Model(s)  Kimi Dev 72B   moonshotai/Kimi-Dev-72B
Model Size72b
Required VRAM77.1 GB
Updated2026-08-05
Maintainermlx-community
Model Typeqwen2
Model Files  5.2 GB: 1-of-15   5.2 GB: 2-of-15   5.3 GB: 3-of-15   5.3 GB: 4-of-15   5.2 GB: 5-of-15   5.3 GB: 6-of-15   5.3 GB: 7-of-15   5.2 GB: 8-of-15   5.3 GB: 9-of-15   5.3 GB: 10-of-15   5.2 GB: 11-of-15   5.3 GB: 12-of-15   5.3 GB: 13-of-15   5.2 GB: 14-of-15   3.5 GB: 15-of-15
Quantization Type8bit
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.43.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Kimi Dev 72B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Kimi Dev 72B 4bit DWQ128K / 40.9 GB446521
Kimi Dev 72B 5bit128K / 50.1 GB3682
Qwen2.5 72B Bnb 4bit128K / 41.4 GB1531
...in 2.9.2 Qwen2 72B 6.0bpw EXL2128K / 56.1 GB51
Qwen2 72B Bnb 4bit128K / 41.2 GB994
...Qwen2 72B 4 0bpw H6 EXL2 Pippa128K / 38.6 GB71
...phin 292 Qwen2 72b EXL2 4 0bpw128K / 38.6 GB41
Qwen2 72B 4bit128K / 40.9 GB510
...n 2.9.2 Qwen72b 8.0bpw H8 EXL2128K / 66.8 GB32
...B Instruct 2.0bpw H Novel EXL2125K / 23 GB41
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Kimi-Dev-72B-8bit.