LLM EXPLORER 62,404 MODELS INDEXED

ThinkingCap Qwen3.8 27B Mlx Mxfp8 by airagrp

By airagrp · 76 downloads
HF Repo ↗ Copy URL

ThinkingCap Qwen3.8 27B Mlx Mxfp8 is an open-source language model by airagrp. Features: 27b LLM, VRAM: 31.1GB, License: other, LLM Explorer Score: 0.29.

  8-bit Base model:bottlecapai/thinkin... Base model:finetune:bottlecapa...   Conversational   En   Image-text-to-text   Mixed-precision   Mlx   Mlx-vlm   Mtp   Multimodal   Mxfp8   Qwen3 5   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Video   Vision
Model Card on HF 🤗: https://huggingface.co/airagrp/ThinkingCap-Qwen3.8-27B-mlx-mxfp8 

ThinkingCap Qwen3.8 27B Mlx Mxfp8 Parameters and Internals

LLM NameThinkingCap Qwen3.8 27B Mlx Mxfp8
Repository 🤗https://huggingface.co/airagrp/ThinkingCap-Qwen3.8-27B-mlx-mxfp8 
Base Model(s)  bottlecapai/ThinkingCap-Qwen3.8-27B   bottlecapai/ThinkingCap-Qwen3.8-27B
Model Size27b
Required VRAM31.1 GB
Updated2026-09-28
Maintainerairagrp
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-6   5.3 GB: 2-of-6   5.4 GB: 3-of-6   5.3 GB: 4-of-6   5.4 GB: 5-of-6   4.4 GB: 6-of-6   0.8 GB
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to ThinkingCap Qwen3.8 27B Mlx Mxfp8

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB1742
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.5 27B0K / 55.2 GB25362941028
Qwen3.6 27B FP80K / 0.4 GB7740472342
Note: green Score (e.g. "73.2") means that the model is better than airagrp/ThinkingCap-Qwen3.8-27B-mlx-mxfp8.