Olmo 3 32B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
The flagship Olmo 3, with a Think variant for reasoning work. Fits a 24 GB card at Q4 with room for context.
Olmo 3 32B needs about 20 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 11.3 GB | ~58 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 14.4 GB | ~46 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 20.1 GB | ~34 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 23.5 GB | ~30 tok/s | Tight | |
| Q6_K 6.56 bpw | 27 GB | ~4 tok/s | Offload | |
| Q8_0 8.50 bpw | 34.8 GB | ~3 tok/s | Offload | |
| F16 16.00 bpw | 64.8 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Olmo 3 32B VRAM calculator →
Get Olmo 3 32B running
The cheapest catalogued GPU that runs Olmo 3 32B is the AMD Radeon RX 7900 XTX (24 GB).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Olmo 3 32B
Install Ollama, then run:
ollama run olmo-3Specifications
Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed. Still unconfirmed: context.
- Parameters
- 32 Billion
- Context window
- 65,536
- Architecture
- Dense
- Provider
- Ai2 (Allen Institute for AI)
- Licence
- Apache 2.0
- Practical deployment
- Single consumer GPU
- Specified at
- Q4_K_M
- System RAM
- 32 GB
- Record updated
- 2026-09-19
Commercial use permitted. No usage restrictions beyond attribution.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Other Olmo 3 sizes
Olmo 3 32B — frequently asked questions
How much VRAM does Olmo 3 32B need?
About 20 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Olmo 3 32B run on an RTX 4090 (24 GB)?
Yes. Olmo 3 32B needs about 20 GB at Q4_K_M, inside a 24 GB card, at an estimated 34 tokens/sec.
How do I run Olmo 3 32B locally?
Install Ollama and run `ollama run olmo-3`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Olmo 3 come in?
Olmo 3 7B (5 GB), Olmo 3 32B (20 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.