LLM EXPLORER 56,604 MODELS INDEXED

Inkling Small MLX Mixed 2bit by Sawfwair

By Sawfwair · 245 downloads
HF Repo ↗ Copy URL

Inkling Small MLX Mixed 2bit is an open-source language model by Sawfwair. Features: 26.2b LLM, VRAM: 84GB, License: apache-2.0, Quantized.

  2-bit   2bit Base model:quantized:thinkingm... Base model:thinkingmachines/in...   Conversational   En   Image-text-to-text   Inkling   Mixed-precision   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sawfwair/Inkling-Small-MLX-Mixed-2bit 

Inkling Small MLX Mixed 2bit Parameters and Internals

LLM NameInkling Small MLX Mixed 2bit
Repository 🤗https://huggingface.co/Sawfwair/Inkling-Small-MLX-Mixed-2bit 
Base Model(s)  Inkling Small   thinkingmachines/Inkling-Small
Model Size26.2b
Required VRAM84 GB
Updated2026-08-09
MaintainerSawfwair
Model Typeinkling
Model Files  5.3 GB: 1-of-16   5.4 GB: 2-of-16   5.2 GB: 3-of-16   5.3 GB: 4-of-16   5.3 GB: 5-of-16   5.3 GB: 6-of-16   5.3 GB: 7-of-16   5.3 GB: 8-of-16   5.3 GB: 9-of-16   5.3 GB: 10-of-16   5.3 GB: 11-of-16   5.3 GB: 12-of-16   5.3 GB: 13-of-16   5.3 GB: 14-of-16   5.3 GB: 15-of-16   4.5 GB: 16-of-16
Supported Languagesen
Quantization Type2bit
Model ArchitectureInklingForConditionalGeneration
Licenseapache-2.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>