Can olmOCR 7B 0225 preview run on the RX 7900 XT?
Yes. At 8K context the best fit is F16, using about 16.6 GB of the 19.0 GB usable on the RX 7900 XT. Estimated speed ceiling: ~48 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) • | 3.7 GB Fits | 3.9 GB Fits | 5.2 GB Fits | 265 |
| 3-bit (Q3_K_M) • | 4.5 GB Fits | 4.7 GB Fits | 6.0 GB Fits | 210 |
| 4-bit (Q4_K_M) • | 5.3 GB Fits | 5.5 GB Fits | 6.8 GB Fits | 171 |
| 5-bit (Q5_K_M) • | 6.0 GB Fits | 6.2 GB Fits | 7.5 GB Fits | 147 |
| 6-bit (Q6_K) • | 6.7 GB Fits | 7.0 GB Fits | 8.3 GB Fits | 128 |
| 8-bit (Q8_0) • | 8.5 GB Fits | 8.7 GB Fits | 10.0 GB Fits | 99 |
| 16-bit (F16/BF16) | 16.4 GB Fits | 16.6 GB Fits | 17.9 GB Tight | 48 |
• real GGUF file size from bartowski/allenai_olmOCR-7B-0225-preview-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.
More
olmOCR 7B 0225 preview on every GPU and Mac · Every model that runs on the RX 7900 XT · Other models that fit 24 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (allenai/olmOCR-7B-0225-preview), AMD specs. Data as of 2026-11-17.