LLM EXPLORER 59,420 MODELS INDEXED

OLMo 2 0325 32B Instruct 4bit by mlx-community

By mlx-community · 46 downloads
HF Repo ↗ Copy URL

OLMo 2 0325 32B Instruct 4bit is an open-source language model by mlx-community. Features: 32b LLM, VRAM: 18.1GB, Context: 4K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.17.

  4-bit   4bit Base model:allenai/olmo-2-0325... Base model:quantized:allenai/o...   Conversational Dataset:allenai/tulu-3-sft-olm...   En   Endpoints compatible   Instruct   Mlx   Olmo2   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/OLMo-2-0325-32B-Instruct-4bit 

OLMo 2 0325 32B Instruct 4bit Parameters and Internals

LLM NameOLMo 2 0325 32B Instruct 4bit
Repository 🤗https://huggingface.co/mlx-community/OLMo-2-0325-32B-Instruct-4bit 
Base Model(s)  OLMo 2 0325 32B Instruct   allenai/OLMo-2-0325-32B-Instruct
Model Size32b
Required VRAM18.1 GB
Updated2026-07-02
Maintainermlx-community
Model Typeolmo2
Instruction-BasedYes
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   5.3 GB: 3-of-4   2.1 GB: 4-of-4
Supported Languagesen
Quantization Type4bit
Model ArchitectureOlmo2ForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.49.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|pad|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to OLMo 2 0325 32B Instruct 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...o 2 0325 32B Instruct Bnb 4bit4K / 18.3 GB91
OLMo 2 0325 32B Instruct4K / 64.7 GB4110147
OLMo 2 0325 32B Instruct4K / 64.7 GB2651
OLMo 2 0325 32B Instruct GGUF4K / 12 GB132512
OLMo 2 0325 32B DPO4K / 64.7 GB3643
OLMo 2 Instruct Math 32B4K / 64.7 GB225
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/OLMo-2-0325-32B-Instruct-4bit.