Inco Splash on the M1 Max 64GB
llamaperf has 4 Inco Splash reports on the M1 Max 64GB, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.
4 Inco Splash reports on the M1 Max 64GB
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- Qwen3.8 27B · 4-bit group-6433.1 t/s(speculative decoding)
- Qwen3.6 35B · 3B active · 4-bit144.0 t/s(speculative decoding)
- Qwen3.8 27B · 4-bit32.8 t/s(speculative decoding)
- Qwen3.8 27B · 4-bit39.1 t/s(speculative decoding)
Frequently asked
How fast is Inco Splash on the M1 Max 64GB?
llamaperf has 4 Inco Splash reports on the M1 Max 64GB, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.