RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can OLMoE 1B 7B 0924 run on the Mac M3 24GB?

Yes. At 8K context the best fit is F16, using about 14.4 GB of the 16.1 GB usable on the Mac M3 24GB. Estimated speed ceiling: ~39 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •3.4 GB Fits211
3-bit (Q3_K_M) •4.1 GB Fits161
4-bit (Q4_K_M) •4.9 GB Fits128
5-bit (Q5_K_M) •5.6 GB Fits110
6-bit (Q6_K) •6.3 GB Fits95
8-bit (Q8_0) •7.9 GB Fits73
16-bit (F16/BF16) •13.9 GB Fits39

• real GGUF file size from allenai/OLMoE-1B-7B-0924-GGUF. Speed is a bandwidth ceiling (100 GB/s), not a benchmark. Methodology.

More

OLMoE 1B 7B 0924 on every GPU and Mac · Every model that runs on the Mac M3 24GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (allenai/OLMoE-1B-7B-0924), Apple specs. Data as of 2026-11-17.