Can Olmo 3 1025 7B run on the RTX 3080 10GB?
Yes. At 8K context the best fit is Q5_K_M, using about 7.9 GB of the 9.5 GB usable on the RTX 3080 10GB. Estimated speed ceiling: ~146 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 5.1 GB Fits | 5.6 GB Fits | 8.6 GB Tight | 278 |
| 3-bit (Q3_K_M) | 5.9 GB Fits | 6.4 GB Fits | 9.4 GB Tight | 213 |
| 4-bit (Q4_K_M) • | 6.8 GB Fits | 7.3 GB Fits | 10.3 GB No | 170 |
| 5-bit (Q5_K_M) | 7.4 GB Fits | 7.9 GB Fits | 10.9 GB No | 146 |
| 6-bit (Q6_K) • | 8.2 GB Fits | 8.7 GB Tight | 11.7 GB No | 127 |
| 8-bit (Q8_0) • | 9.8 GB No | 10.3 GB No | 13.3 GB No | — |
| 16-bit (F16/BF16) | 16.2 GB No | 16.7 GB No | 19.7 GB No | — |
• real GGUF file size from lmstudio-community/Olmo-3-1025-7B-GGUF. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.
More
Olmo 3 1025 7B on every GPU and Mac · Every model that runs on the RTX 3080 10GB · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (allenai/Olmo-3-1025-7B), NVIDIA specs. Data as of 2026-11-17.