Can OLMoE 1B 7B 0924 run on the RX 7900 XT?
Yes. At 8K context the best fit is F16, using about 14.4 GB of the 19.0 GB usable on the RX 7900 XT. Estimated speed ceiling: ~312 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | Max tok/s (est., 8K) |
|---|---|---|
| 2-bit (Q2_K) • | 3.4 GB Fits | 1685 |
| 3-bit (Q3_K_M) • | 4.1 GB Fits | 1291 |
| 4-bit (Q4_K_M) • | 4.9 GB Fits | 1025 |
| 5-bit (Q5_K_M) • | 5.6 GB Fits | 876 |
| 6-bit (Q6_K) • | 6.3 GB Fits | 760 |
| 8-bit (Q8_0) • | 7.9 GB Fits | 587 |
| 16-bit (F16/BF16) • | 13.9 GB Fits | 312 |
• real GGUF file size from allenai/OLMoE-1B-7B-0924-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.
More
OLMoE 1B 7B 0924 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/OLMoE-1B-7B-0924), AMD specs. Data as of 2026-11-17.