LLM EXPLORER 67,711 MODELS INDEXED

Qwen3.8 Flash Next 4bit Mtp by mlx-community

By mlx-community · 540 downloads

Qwen3.8 Flash Next 4bit Mtp is an open-source language model by mlx-community. Features: 180b LLM, VRAM: 112.9GB, Quantized, LLM Explorer Score: 0.28.

  4-bit   4bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   En   Image-text-to-text   Mlx   Mtp   Quantized   Qwen4 exp   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow

Qwen3.8 Flash Next 4bit Mtp Parameters and Internals

LLM NameQwen3.8 Flash Next 4bit Mtp
Repository πŸ€—https://huggingface.co/mlx-community/Qwen3.8-Flash-Next-4bit-mtp 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size180b
Required VRAM112.9 GB
Updated2026-09-26
Maintainermlx-community
Model Typeqwen4_exp
Model Files  5.3 GB: 1-of-22   5.2 GB: 2-of-22   5.2 GB: 3-of-22   5.2 GB: 4-of-22   5.2 GB: 5-of-22   5.2 GB: 6-of-22   5.1 GB: 7-of-22   5.3 GB: 8-of-22   5.3 GB: 9-of-22   5.0 GB: 10-of-22   5.3 GB: 11-of-22   5.0 GB: 12-of-22   5.3 GB: 13-of-22   5.3 GB: 14-of-22   5.0 GB: 15-of-22   5.3 GB: 16-of-22   5.0 GB: 17-of-22   5.3 GB: 18-of-22   5.3 GB: 19-of-22   5.0 GB: 20-of-22   5.3 GB: 21-of-22   2.1 GB: 22-of-22   1.7 GB: 1-of-1
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen4ExpForConditionalGeneration
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 Flash Next 4bit Mtp

Best Alternatives
Context / RAM
Downloads
Likes
...wen3.8 Flash Next MLX 4bit MTP0K / 112.8 GB446012
...wen3.8 Flash Next MLX 4bit MTP0K / 112.8 GB16435
...3.8 Flash Next OQ3.5e Fp16 Mtp0K / 90.7 GB7661
...en3.8 Flash Next OQ4e Fp16 Mtp0K / 107.6 GB3872
...en3.8 Flash Next OQ4e Fp16 Mtp0K / 107.3 GB7462
...n3.8 Flash Next GSQ RCO Q2 Mlx0K / 4.8 GB4452
...3.8 Flash Next OQ2.5e Fp16 Mtp0K / 83.6 GB2133
...3.8 Flash Next OQ3.5e Fp16 Mtp0K / 97.2 GB1451
...en3.8 Flash Next OQ3e Fp16 Mtp0K / 91.8 GB1321
...MLX Activation 3bit Native PLE0K / 34.7 GB2841
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.8-Flash-Next-4bit-mtp.