LLMs · Ai2

Olmo 3 7B Instruct

Name: Olmo 3 7B Instruct
Author: Ai2

Parameters: 7.3B
Architecture: Dense
Max context: 64K tokens
License: apache-2.0
Released: 2025-11

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run olmo-3:7b-instruct

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

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

huggingface.co/unsloth/Olmo-3-7B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Olmo-3-7B-Instruct-GGUF

Original weights · Hugging Face

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

huggingface.co/allenai/Olmo-3-7B-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.

KV cache: sliding-window hybrid: the KV estimate counts the global-attention layers plus a small allowance for the sliding-window layers.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	2.9 GB	5.0 GB	9.4 GB	GGUF (opens in a new tab)
`Q3_K_M`	Low	3.6 GB	5.7 GB	10.1 GB	GGUF (opens in a new tab)
`Q4_K_M`	Good	4.5 GB	6.5 GB	11.0 GB	GGUF (opens in a new tab)
`Q5_K_M`	High	5.2 GB	7.3 GB	11.7 GB	GGUF (opens in a new tab)
`Q6_K`	High	6.0 GB	8.1 GB	12.5 GB	GGUF (opens in a new tab)
`Q8_0`	Very high	7.7 GB	9.8 GB	14.2 GB	GGUF (opens in a new tab)
`F16`	Full	14.6 GB	16.7 GB	21.1 GB	GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for Olmo 3 7B Instruct

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q3_K_M.

Grade · points	Hardware	Quant	Memory	Speed	Fit
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	AMD Radeon RX 9070 XT	`Q8_0`	10.6 GB / 16.0 GB	47.2 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 4070 Ti SUPER	`Q8_0`	10.6 GB / 16.0 GB	57.5 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 4080 SUPER	`Q8_0`	10.6 GB / 16.0 GB	63.0 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 5070 Ti	`Q8_0`	10.6 GB / 16.0 GB	76.7 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 5080	`Q8_0`	10.6 GB / 16.0 GB	82.2 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Intel Arc B580	`Q6_K`	8.7 GB / 12.0 GB	40.6 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 3060 12GB	`Q6_K`	8.7 GB / 12.0 GB	42.0 tok/s	Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 4070 SUPER	`Q6_K`	8.7 GB / 12.0 GB	58.8 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.2/15	NVIDIA GeForce RTX 5090	`F16`	18.3 GB / 32.0 GB	70.7 tok/s	Runs well
75 ptsGreat (A) · 75 of 100 points: Model quality 21.8/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15	NVIDIA GeForce RTX 4060	`Q5_K_M`	7.7 GB / 8.0 GB	37.8 tok/s	Tight fit

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.