LLM EXPLORER 63,069 MODELS INDEXED

Qwen3.8 Flash Next GSQ RCO Q2 Mlx by NovaeonStudio

By NovaeonStudio · 445 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next GSQ RCO Q2 Mlx is an open-source language model by NovaeonStudio. Features: 180b LLM, VRAM: 4.8GB, License: other, Quantized, LLM Explorer Score: 0.32.

  Arxiv:2604.18556   Arxiv:2605.00649   4-bit   4bit   Apple-silicon Base model:ista-daslab/qwen3.8... Base model:quantized:ista-dasl...   Conversational   Gsq   Image-text-to-text   Mixed-precision   Mlx   Moe   Mtp   Omlx   Q2   Quantized   Qwen4 exp   Rco   Region:us   Safetensors   Sharded   Ssd-offload   Tensorflow
Model Card on HF 🤗: https://huggingface.co/NovaeonStudio/Qwen3.8-Flash-Next-GSQ-RCO-Q2-mlx 

Qwen3.8 Flash Next GSQ RCO Q2 Mlx Parameters and Internals

LLM NameQwen3.8 Flash Next GSQ RCO Q2 Mlx
Repository 🤗https://huggingface.co/NovaeonStudio/Qwen3.8-Flash-Next-GSQ-RCO-Q2-mlx 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF   mlx-community/Qwen3.8-Flash-Next-4bit   Qwen/Qwen3.8-Flash-Next   ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF   mlx-community/Qwen3.8-Flash-Next-4bit
Model Size180b
Required VRAM4.8 GB
Updated2026-10-05
MaintainerNovaeonStudio
Model Typeqwen4_exp
Model Files  1.4 GB: 1-of-22   0.1 GB: 7-of-22   0.2 GB: 8-of-22   0.2 GB: 9-of-22   0.2 GB: 10-of-22   0.2 GB: 11-of-22   0.2 GB: 12-of-22   0.2 GB: 13-of-22   0.2 GB: 14-of-22   0.2 GB: 15-of-22   0.2 GB: 16-of-22   0.2 GB: 17-of-22   0.2 GB: 18-of-22   0.2 GB: 19-of-22   0.2 GB: 20-of-22   0.2 GB: 21-of-22   0.5 GB: 22-of-22   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB   0.8 GB
Quantization Typeq2|4bit
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Transformers Version5.8.0.dev0

Best Alternatives to Qwen3.8 Flash Next GSQ RCO Q2 Mlx

Best Alternatives
Context / RAM
Downloads
Likes
...wen3.8 Flash Next MLX 4bit MTP0K / 112.8 GB446012
...3.8 Flash Next OQ3.5e Fp16 Mtp0K / 90.7 GB7661
Qwen3.8 Flash Next 4bit Mtp0K / 112.9 GB5403
...en3.8 Flash Next OQ4e Fp16 Mtp0K / 107.3 GB7462
...wen3.8 Flash Next MLX 4bit MTP0K / 112.8 GB16435
...MLX Activation 3bit Native PLE0K / 34.7 GB2841
Qwen3.8 Flash Next0K / 129.5 GB48103918
Darwin 180B RSI0K / 119 GB35394
...Qwen3.8 Flash Next Abliterated0K / 129.5 GB49342
Qwen3.8 Flash Next FP80K / 65.7 GB2219117
Note: green Score (e.g. "73.2") means that the model is better than NovaeonStudio/Qwen3.8-Flash-Next-GSQ-RCO-Q2-mlx.