LLM EXPLORER 55,709 MODELS INDEXED

Inkling Small Mlx 4bit by mlx-community

By mlx-community · 415 downloads
HF Repo ↗ Copy URL

Inkling Small Mlx 4bit is an open-source language model by mlx-community. Features: 44.2b LLM, VRAM: 153.3GB, License: apache-2.0, Quantized.

  4bit   Apple-silicon Base model:finetune:thinkingma... Base model:thinkingmachines/in...   Conversational   Image-text-to-text   Inkling   Inkling mm model   Mlx   Moe   Multimodal   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Inkling-Small-mlx-4bit 

Inkling Small Mlx 4bit Parameters and Internals

LLM NameInkling Small Mlx 4bit
Repository 🤗https://huggingface.co/mlx-community/Inkling-Small-mlx-4bit 
Base Model(s)  Inkling Small   thinkingmachines/Inkling-Small
Model Size44.2b
Required VRAM153.3 GB
Updated2026-08-08
Maintainermlx-community
Model Typeinkling_mm_model
Model Files  6.0 GB: 1-of-30   5.0 GB: 2-of-30   5.0 GB: 3-of-30   5.9 GB: 4-of-30   5.2 GB: 5-of-30   5.1 GB: 6-of-30   5.2 GB: 7-of-30   5.1 GB: 8-of-30   5.0 GB: 9-of-30   5.0 GB: 10-of-30   5.0 GB: 11-of-30   5.0 GB: 12-of-30   5.0 GB: 13-of-30   5.0 GB: 14-of-30   5.0 GB: 15-of-30   5.0 GB: 16-of-30   5.3 GB: 17-of-30   5.1 GB: 18-of-30   5.1 GB: 19-of-30   5.2 GB: 20-of-30   5.0 GB: 21-of-30   6.1 GB: 22-of-30   5.2 GB: 23-of-30   5.0 GB: 24-of-30   5.0 GB: 25-of-30   5.0 GB: 26-of-30   5.2 GB: 27-of-30   5.0 GB: 28-of-30   5.9 GB: 29-of-30   2.7 GB: 30-of-30
Quantization Type4bit
Model ArchitectureInklingForConditionalGeneration
Licenseapache-2.0
Tokenizer ClassPreTrainedTokenizerFast