APPLE · 128GB unified memory · 5 reports
Use the calculator to check which models fit in 128 GB of unified memory. The reports below include different GPU counts and memory setups; a model listed here may need extra cards or CPU offloading.
How to compare these reports →All M4 Macs compared →M4 Max 128GB · WebGPU
Reported by the source; GPU count, offloading and concurrent requests can change this figure. Check the full setup before comparing.
User reports running a model in-browser with custom WebGPU kernels, at speed comparable to llama.cpp.
Reported by the source; GPU count, offloading and concurrent requests can change this figure. Check the full setup before comparing.
User benchmarks Qwen3.6-35B-A3B on a Mac with OMLX, comparing MTP enabled against disabled. MTP shows minimal speedup for the 35B MoE model but roughly 2x for the 27B dense model. Results include pp and tg t/s at various context lengths and batch sizes.
M4 Max 128GB · 256,000 ctx
Reported by the source; GPU count, offloading and concurrent requests can change this figure. Check the full setup before comparing.
User benchmarks Qwen3.8 27B on an M4 Max 128GB across five runtime and quant stacks at contexts from 32K to 256K. The stacks are oMLX AWQ 5-bit, oMLX oQ8e, mlx-dspark, and MTPLX 4-bit and 8-bit. Best decode at 256K is oMLX AWQ 5-bit at 15.2 t/s, while MTPLX collapses at 256K. Prefix caching is crucial for effective speed.
User reports GLM 5.3 Flash support in the ds4 branch, running on an M4 Max with 128 GB. No performance numbers are provided.
User reports Qwen 3.8 27B as the first model to break 94% on the cupel benchmark. Setup is llama.cpp with the unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS quant, which outperformed other 4-bit quants. Qwen 3.8 27B outperformed in coding but lost in general knowledge to Gemma 31B and Qwen 3.6.