Check my GPU

LLMs ·

OLMo 2 32B Instruct

Parameters
32B
Architecture
Dense
Max context
4K tokens
License
apache-2.0
Released
2025-03

How to run it

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/allenai/OLMo-2-0325-32B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/allenai/OLMo-2-0325-32B-Instruct-GGUF

Original weights · Hugging Face

Full-precision files from Ai2, for fine-tuning, vLLM, Transformers.

huggingface.co/allenai/OLMo-2-0325-32B-Instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Ai2. The weights themselves download from Hugging Face.

github.com/allenai/OLMo (opens in a new tab)

git clone https://github.com/allenai/OLMo

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization Quality Weights Total at 4K context Download
Q2_K Low 12.9 GB 14.6 GB GGUF files (opens in a new tab)
Q3_K_M Low 15.8 GB 17.5 GB GGUF (opens in a new tab)
Q4_K_M Good 19.7 GB 21.3 GB GGUF (Q4_K_S) (opens in a new tab)
Q5_K_M High 22.9 GB 24.6 GB GGUF (Q5_K_S) (opens in a new tab)
Q6_K High 26.4 GB 28.1 GB GGUF files (opens in a new tab)
Q8_0 Very high 34.2 GB 35.8 GB GGUF (opens in a new tab)
F16 Full 64.5 GB 66.1 GB Original weights (opens in a new tab)

Best hardware for OLMo 2 32B Instruct

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7600 XT (launch price $329) at Q2_K.

Grade · points Hardware Quant Memory Speed Fit
81 ptsGreat (A) · 81 of 100 points: Model quality 26.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q5_K_M 26.2 GB / 32.0 GB 56.4 tok/s Runs well
79 ptsGreat (A) · 79 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q4_K_M 22.5 GB / 24.0 GB 38.4 tok/s Tight fit
78 ptsGreat (A) · 78 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.2/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q4_K_M 22.5 GB / 24.0 GB 35.6 tok/s Tight fit
77 ptsGreat (A) · 77 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 13.3/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q4_K_M 22.5 GB / 24.0 GB 31.5 tok/s Tight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 26.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15 NVIDIA RTX PRO 6000 Blackwell Q6_K 32.9 GB / 96.0 GB 47.4 tok/s Runs well
72 ptsGreat (A) · 72 of 100 points: Model quality 18.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER Q2_K 15.4 GB / 16.0 GB 42.0 tok/s Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 18.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER Q2_K 15.4 GB / 16.0 GB 46.0 tok/s Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 18.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti Q2_K 15.4 GB / 16.0 GB 56.0 tok/s Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 18.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 Q2_K 15.4 GB / 16.0 GB 60.0 tok/s Tight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 10.0/15, Memory use 12.1/15 Apple M4 Max (64 GB) Q4_K_M 25.2 GB / 48.0 GB 17.9 tok/s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.