LLM EXPLORER 65,695 MODELS INDEXED

Qwen3.8 Flash Next RAM 91GB MLX by baa-ai

By baa-ai · 173 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next RAM 91GB MLX is an open-source language model by baa-ai. Features: 177.4b LLM, VRAM: 90.6GB, License: other, LLM Explorer Score: 0.31.

  3-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Image-text-to-text   Mixed-precision   Mlx   Moe   Quantized   Qwen   Qwen3.8   Qwen4 exp   Region:us   Safetensors   Sharded   Tensorflow   Vision   Vision-language
Model Card on HF 🤗: https://huggingface.co/baa-ai/Qwen3.8-Flash-Next-RAM-91GB-MLX 

Qwen3.8 Flash Next RAM 91GB MLX Parameters and Internals

LLM NameQwen3.8 Flash Next RAM 91GB MLX
Repository 🤗https://huggingface.co/baa-ai/Qwen3.8-Flash-Next-RAM-91GB-MLX 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size177.4b
Required VRAM90.6 GB
Updated2026-10-26
Maintainerbaa-ai
Model Typeqwen4_exp
Model Files  5.3 GB: 1-of-18   5.2 GB: 2-of-18   5.2 GB: 3-of-18   5.2 GB: 4-of-18   5.2 GB: 5-of-18   5.2 GB: 6-of-18   5.1 GB: 7-of-18   5.2 GB: 8-of-18   5.1 GB: 9-of-18   5.1 GB: 10-of-18   5.2 GB: 11-of-18   5.1 GB: 12-of-18   5.1 GB: 13-of-18   5.2 GB: 14-of-18   5.1 GB: 15-of-18   5.1 GB: 16-of-18   5.2 GB: 17-of-18   2.8 GB: 18-of-18
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen3_5Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 Flash Next RAM 91GB MLX

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 Flash Next Heretic0K / 355.1 GB960
Qwen3.8 Flash Next Heretic 20K / 355.1 GB643
Qwen3.8 Flash Next OptiQ 2bit0K / 79.9 GB6711
Qwen3.8 Flash Next 4bit0K / 111.2 GB5552
...lash Next Saikei V1.0 4bit Mlx0K / 111.8 GB1240
Qwen3.8 Flash Next JANG 1L0K / 64.5 GB6372