LLM EXPLORER 59,420 MODELS INDEXED

Kimi Dev 72B 4bit DWQ by mlx-community

By mlx-community · 4465 downloads
HF Repo ↗ Copy URL

Kimi Dev 72B 4bit DWQ is an open-source language model by mlx-community. Features: 72b LLM, VRAM: 40.9GB, Context: 128K, License: mit, Quantized, LLM Explorer Score: 0.22.

  4-bit   4bit 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-4bit-DWQ 

Kimi Dev 72B 4bit DWQ Parameters and Internals

LLM NameKimi Dev 72B 4bit DWQ
Repository 🤗https://huggingface.co/mlx-community/Kimi-Dev-72B-4bit-DWQ 
Base Model(s)  Kimi Dev 72B   moonshotai/Kimi-Dev-72B
Model Size72b
Required VRAM40.9 GB
Updated2026-08-06
Maintainermlx-community
Model Typeqwen2
Model Files  5.4 GB: 1-of-8   5.3 GB: 2-of-8   5.3 GB: 3-of-8   5.3 GB: 4-of-8   5.3 GB: 5-of-8   5.3 GB: 6-of-8   5.3 GB: 7-of-8   3.7 GB: 8-of-8
Quantization Type4bit
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 4bit DWQ

Best Alternatives
Context / RAM
Downloads
Likes
Kimi Dev 72B 8bit128K / 77.1 GB3612
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