LLM EXPLORER 56,604 MODELS INDEXED

Inkling Small MLX 4bit by pipenetwork

By pipenetwork · 357 downloads
HF Repo ↗ Copy URL

Inkling Small MLX 4bit is an open-source language model by pipenetwork. Features: 41.2b LLM, VRAM: 148.3GB, License: apache-2.0, Quantized.

  4bit Base model:quantized:thinkingm... Base model:thinkingmachines/in...   Conversational   Image-text-to-text   Inkling   Inkling mm model   Mlx   Moe   Multimodal   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Thinking-machines
Model Card on HF 🤗: https://huggingface.co/pipenetwork/Inkling-Small-MLX-4bit 

Inkling Small MLX 4bit Parameters and Internals

LLM NameInkling Small MLX 4bit
Repository 🤗https://huggingface.co/pipenetwork/Inkling-Small-MLX-4bit 
Base Model(s)  Inkling Small   thinkingmachines/Inkling-Small
Model Size41.2b
Required VRAM148.3 GB
Updated2026-08-09
Maintainerpipenetwork
Model Typeinkling_mm_model
Model Files  6.0 GB: 1-of-28   5.0 GB: 2-of-28   6.0 GB: 3-of-28   5.0 GB: 4-of-28   5.0 GB: 5-of-28   6.0 GB: 6-of-28   5.0 GB: 7-of-28   5.0 GB: 8-of-28   6.1 GB: 9-of-28   5.1 GB: 10-of-28   5.0 GB: 11-of-28   6.0 GB: 12-of-28   5.0 GB: 13-of-28   6.0 GB: 14-of-28   5.0 GB: 15-of-28   5.2 GB: 16-of-28   5.0 GB: 17-of-28   5.0 GB: 18-of-28   5.0 GB: 19-of-28   6.0 GB: 20-of-28   5.0 GB: 21-of-28   6.0 GB: 22-of-28   5.0 GB: 23-of-28   6.1 GB: 24-of-28   5.3 GB: 25-of-28   6.1 GB: 26-of-28   6.0 GB: 27-of-28   1.4 GB: 28-of-28
Quantization Type4bit
Model ArchitectureInklingForConditionalGeneration
Licenseapache-2.0
Tokenizer ClassPreTrainedTokenizerFast