Can OLMoE 1B 7B 0924 run on the RTX A6000?
Yes. At 8K context the best fit is F16, using about 14.4 GB of the 45.6 GB usable on the RTX A6000. Estimated speed ceiling: ~299 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | Max tok/s (est., 8K) |
|---|---|---|
| 2-bit (Q2_K) • | 3.4 GB Fits | 1617 |
| 3-bit (Q3_K_M) • | 4.1 GB Fits | 1240 |
| 4-bit (Q4_K_M) • | 4.9 GB Fits | 984 |
| 5-bit (Q5_K_M) • | 5.6 GB Fits | 841 |
| 6-bit (Q6_K) • | 6.3 GB Fits | 729 |
| 8-bit (Q8_0) • | 7.9 GB Fits | 563 |
| 16-bit (F16/BF16) • | 13.9 GB Fits | 299 |
• real GGUF file size from allenai/OLMoE-1B-7B-0924-GGUF. Speed is a bandwidth ceiling (768 GB/s), not a benchmark. Methodology.
More
OLMoE 1B 7B 0924 on every GPU and Mac · Every model that runs on the RTX A6000 · Other models that fit 48 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (allenai/OLMoE-1B-7B-0924), NVIDIA specs. Data as of 2026-11-17.