GPUfit — Apple M1 Maxhttps://gpufit.tech/mac/m1-maxNew catalog models scored against Apple M1 Max.bottlecapai ThinkingCap gemma 4 26B A4B it on Apple M1 Max: Runshttps://gpufit.tech/models/bottlecapai-thinkingcap-gemma-4-26b-a4b-ithttps://gpufit.tech/models/bottlecapai-thinkingcap-gemma-4-26b-a4b-itFri, 23 Oct 2026 21:26:38 GMTRuns fully in unified memory on your Apple M1 Max at Q5_K_M, 8K context, about 42–58 tok/s. Weights 18.6 GB plus 0.51 GB of KV cache — 19.6 GB of 24.0 GB usable. Up to 64K context still fits. 42–58 tok/s.NVIDIA Nemotron 3.5 Bolt E4B on Apple M1 Max: Runshttps://gpufit.tech/models/nvidia-nemotron-3-5-bolt-e4bhttps://gpufit.tech/models/nvidia-nemotron-3-5-bolt-e4bFri, 23 Oct 2026 09:47:55 GMTRuns fully in unified memory on your Apple M1 Max at BF16, 8K context, about 14–19 tok/s. Weights 14.0 GB plus 0.14 GB of KV cache — 14.6 GB of 24.0 GB usable. Up to 128K context still fits. 14–19 tok/s.DeepSeek V4.1 Flash 1017 on Apple M1 Max: Won't fithttps://gpufit.tech/models/deepseek-v4-1-flash-1017https://gpufit.tech/models/deepseek-v4-1-flash-1017Sat, 17 Oct 2026 20:36:06 GMTWon't fit on Apple M1 Max. The smallest quant UD-IQ1_S is 217.0 GB before KV cache, and usable memory is 24.0 GB.LFM2.5 24B A2B on Apple M1 Max: Tight fithttps://gpufit.tech/models/lfm2-5-24b-a2bhttps://gpufit.tech/models/lfm2-5-24b-a2bTue, 13 Oct 2026 14:19:48 GMTTight fit fully in unified memory on your Apple M1 Max at UD-Q6_K_XL, 8K context, about 88–120 tok/s. Weights 20.4 GB plus 0.63 GB of KV cache — 21.5 GB of 24.0 GB usable. Up to 32K context still fits. 88–120 tok/s.