LLM EXPLORER 55,709 MODELS INDEXED

Inkling Mlx 2bit by mlx-community

By mlx-community · 3045 downloads
HF Repo ↗ Copy URL

Inkling Mlx 2bit is an open-source language model by mlx-community. Features: 98.9b LLM, VRAM: 225.6GB, License: apache-2.0, Quantized, ELO: 1442.

  2bit 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-mlx-2bit 

Inkling Mlx 2bit Benchmarks

LMSys ELO 1442 vs 1272 (so35) 13.4%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Inkling Mlx 2bit Parameters and Internals

LLM NameInkling Mlx 2bit
Repository 🤗https://huggingface.co/mlx-community/Inkling-mlx-2bit 
Base Model(s)  Inkling   thinkingmachines/Inkling
Model Size98.9b
Required VRAM225.6 GB
Updated2026-08-08
Maintainermlx-community
Model Typeinkling_mm_model
Model Files  5.1 GB: 1-of-58   5.0 GB: 1-of-65   6.1 GB: 2-of-58   5.0 GB: 2-of-65   5.1 GB: 3-of-58   5.0 GB: 3-of-65   6.0 GB: 4-of-58   5.0 GB: 4-of-65   5.1 GB: 5-of-58   5.0 GB: 5-of-65   5.0 GB: 6-of-58   5.0 GB: 6-of-65   5.8 GB: 7-of-58   5.0 GB: 7-of-65   5.1 GB: 8-of-58   5.0 GB: 8-of-65   6.1 GB: 9-of-58   5.0 GB: 9-of-65   5.0 GB: 10-of-58   5.0 GB: 10-of-65   5.1 GB: 11-of-58   5.0 GB: 11-of-65   6.1 GB: 12-of-58   5.0 GB: 12-of-65   5.0 GB: 13-of-58   5.0 GB: 13-of-65   5.1 GB: 14-of-58   5.0 GB: 14-of-65   6.2 GB: 15-of-58   5.0 GB: 15-of-65   6.0 GB: 16-of-58   5.0 GB: 16-of-65   5.3 GB: 17-of-58   5.0 GB: 17-of-65   5.0 GB: 18-of-58   5.0 GB: 18-of-65   6.1 GB: 19-of-58   5.0 GB: 19-of-65   5.1 GB: 20-of-58   5.0 GB: 20-of-65   6.1 GB: 21-of-58   5.0 GB: 21-of-65   5.1 GB: 22-of-58
Quantization Type2bit
Model ArchitectureInklingForConditionalGeneration
Licenseapache-2.0