Written by Jakub Rusinowski · Last updated September 19, 2026
Model library → Olmo 3 → Olmo 3 32B
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.
| Parameters | 32 Billion |
| Context window | 65,536 |
| Architecture | Dense |
| Provider | Ai2 (Allen Institute for AI) |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 32 GB |
| Record updated | 2026-09-19 |
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.
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB). Weights plus framework overhead only — this model publishes no architecture we can read, so no KV cache is included. A real session needs more; the figure is a floor, not a target. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Bits/weight | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|---|
| Q2_K | 2.63 | 10.5 GB | 11.3 GB | ~58 tok/s (est.) | Fits comfortably |
| Q3_K_M | 3.41 | 13.6 GB | 14.4 GB | ~46 tok/s (est.) | Fits comfortably |
| Q4_K_M | 4.83 | 19.3 GB | 20.1 GB | ~34 tok/s (est.) | Fits comfortably |
| Q5_K_M | 5.67 | 22.7 GB | 23.5 GB | ~30 tok/s (est.) | Tight fit |
| Q6_K | 6.56 | 26.2 GB | 27 GB | ~4 tok/s (est.) | Offloads to system RAM (slow) |
| Q8_0 | 8.50 | 34 GB | 34.8 GB | ~3 tok/s (est.) | Offloads to system RAM (slow) |
| F16 | 16.00 | 64 GB | 64.8 GB | — | Won't fit |
Want to set your own context length and KV-cache quantization? Use the interactive VRAM calculator.
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.
The cheapest catalogued GPU that runs Olmo 3 32B is the AMD Radeon RX 7900 XT (20 GB).
Install Ollama, then run:
ollama run olmo-3Weights on Hugging Face: allenai/Olmo-3-1125-32B.
Best for: research, reproducibility, reasoning, chat.
← All Olmo 3 models | VRAM calculator | Check your own hardware