AI Index

Open-weight models that run on Apple M4 Max (32-core GPU) · 36 GB

  • Unified memory 36 GB
  • Bandwidth 410 GB/s
  • Usable 24.0 GB

Specs: Memory · MacBook Pro (16-inch, 2024) - Tech Specs - Apple Support · Bandwidth · MacBook Pro (16-inch, 2024) - Tech Specs - Apple Support

FitModelParameters / activePrecisionMemoryEst. speedLongest contextRuns as
Runs wellQwen3.5-35B-A3B Alibaba Qwen36B / 3BQ4_K_M21.5 / 24.0 GB103–155 tok/s135KUnified memory
Runs wellQwen3.6-35B-A3B Alibaba Qwen36B / 3BQ4_K_M21.5 / 24.0 GB103–155 tok/s135KUnified memory
Runs wellQwen3-Omni-30B-A3B-Captioner Alibaba Qwen31.7BQ4_K_M19.6 / 24.0 GB58–86 tok/s55KUnified memory
Runs wellGLM-4.7-Flash Zhipu AI31.2BQ5_021.4 / 24.0 GB51–77 tok/s58KUnified memory
Runs wellQwen3-VL-30B-A3B-Instruct Alibaba Qwen31.1BQ4_K_Mmaker’s file18.9 / 24.0 GB66–98 tok/s62KUnified memory
Runs wellQwen3-VL-30B-A3B-Thinking Alibaba Qwen31.1BQ4_K_Mmaker’s file18.9 / 24.0 GB66–98 tok/s62KUnified memory
Runs wellQwen3-30B-A3B-Instruct-2507 Alibaba Qwen30.5B / 3.3BQ5_021.3 / 24.0 GB67–100 tok/s37KUnified memory
Runs wellQwen3-30B-A3B-Thinking-2507 Alibaba Qwen30.5B / 3.3BQ5_021.3 / 24.0 GB67–100 tok/s37KUnified memory
Runs wellQwen3-30B-A3B Alibaba Qwen30.5B / 3.3BQ5_0maker’s file21.4 / 24.0 GB66–100 tok/s36KUnified memory
Runs wellQwen3-Coder-30B-A3B-Instruct Alibaba Qwen30.5B / 3.3BQ5_021.3 / 24.0 GB67–100 tok/s37KUnified memory
Runs wellHy-Memory-30B-A3B Tencent30.1B / 3BQ5_021.0 / 24.0 GB71–107 tok/s40KUnified memory
Runs wellQwen3.5-27B Alibaba Qwen27.8BQ4_015.8 / 24.0 GB13–19 tok/s139KUnified memory
Runs wellQwen3.6-27B Alibaba Qwen27.8BQ4_015.8 / 24.0 GB13–19 tok/s139KUnified memory
Runs wellQwen3.8-27B Alibaba Qwen27.8BQ4_015.8 / 24.0 GB13–19 tok/s139KUnified memory
Runs wellGemma 4 26B A4B IT Google25.8B / 3.8BQ6_K21.2 / 24.0 GB56–84 tok/s79KUnified memory
Runs wellMagistral Small 1.2 Mistral AI24BQ4_K_Mmaker’s file15.3 / 24.0 GB13–20 tok/s63KUnified memory
Runs wellDevstral Small 1.0 Mistral AI23.6BQ4_K_M15.3 / 24.0 GB13–20 tok/s64KUnified memory
Runs wellDevstral Small 1.1 Mistral AI23.6BQ4_K_M15.3 / 24.0 GB13–20 tok/s64KUnified memory
Runs wellMagistral Small 1.0 Mistral AI23.6BQ4_K_M15.3 / 24.0 GB13–20 tok/s39KUnified memory
Runs wellMagistral Small 1.1 Mistral AI23.6BQ4_K_Mmaker’s file15.3 / 24.0 GB13–20 tok/s39KUnified memory
Runs wellERNIE-4.5-21B-A3B-Thinking Baidu21.8B / 3BQ6_K18.0 / 24.0 GB70–105 tok/s118KUnified memory
Runs wellGPT OSS 20B OpenAI20.9B / 3.6BMXFP4 (native)maker’s file13.6 / 24.0 GB80–120 tok/s128KUnified memory
Runs wellQwen2.5-14B-Instruct-1M Alibaba Qwen14.8BFP815.9 / 24.0 GB13–19 tok/s51KUnified memory
Runs wellQwen2.5-14B-Instruct Alibaba Qwen14.8BFP815.9 / 24.0 GB13–19 tok/s32KUnified memory
Runs wellDeepSeek-R1-Distill-Qwen-14B DeepSeek14.8BFP815.9 / 24.0 GB13–19 tok/s32KUnified memory
Runs wellQwen3-14B Alibaba Qwen14.8BQ6_Kmaker’s file13.1 / 24.0 GB15–23 tok/s128KUnified memory
Runs wellGemma 3 12B IT Google12.2BQ8_015.5 / 24.0 GB13–19 tok/s32KUnified memory
Runs wellQwen2.5-Omni-7B Alibaba Qwen10.7BQ8_011.6 / 24.0 GB17–26 tok/s32KUnified memory
Runs wellGLM-4.6V-Flash Zhipu AI10.3BQ8_011.0 / 24.0 GB18–27 tok/s125KUnified memory
Runs wellQwen3.5-9B Alibaba Qwen9.7BQ8_010.3 / 24.0 GB19–29 tok/s256KUnified memory
Runs wellQianfan-VL-8B Baidu8.8BQ8_010.2 / 24.0 GB20–29 tok/s32KUnified memory
Runs wellGranite Switch 4.1 8B IBM8.8BQ8_0maker’s file11.2 / 24.0 GB18–27 tok/s86KUnified memory
Runs wellQwen3-VL-8B-Instruct Alibaba Qwen8.8BQ8_0maker’s file9.7 / 24.0 GB21–31 tok/s109KUnified memory
Runs wellQwen3-VL-8B-Thinking Alibaba Qwen8.8BQ8_0maker’s file9.7 / 24.0 GB21–31 tok/s109KUnified memory
Runs wellpplx-embed-v2-context-9b Perplexity8.4BQ8_09.1 / 24.0 GB22–33 tok/s256KUnified memory
Runs wellQwen2.5-VL-7B-Instruct Alibaba Qwen8.3BQ8_09.1 / 24.0 GB22–33 tok/s125KUnified memory
Runs wellQwen3-8B Alibaba Qwen8.2BMLX 8bitmaker’s file9.5 / 24.0 GB21–32 tok/s128KUnified memory
Runs wellDeepSeek-R1-Distill-Llama-8B DeepSeek8BQ8_09.4 / 24.0 GB21–32 tok/s124KUnified memory
Runs wellGemma 4 E4B Google8BBF16 (native)maker’s file15.8 / 24.0 GB13–19 tok/s125KUnified memory
Runs wellLing-3.0-tiny Ant Group7.9B / 1.3BBF16 (native)maker’s file15.6 / 24.0 GB73–109 tok/s128KUnified memory
Runs wellQwen2.5-7B-Instruct-1M Alibaba Qwen7.6BBF16 (native)maker’s file15.3 / 24.0 GB13–20 tok/s166KUnified memory
Runs wellQwen2.5-7B-Instruct Alibaba Qwen7.6BBF16 (native)maker’s file15.3 / 24.0 GB13–20 tok/s32KUnified memory
Runs wellDeepSeek-R1-Distill-Qwen-7B DeepSeek7.6BBF16 (native)maker’s file15.3 / 24.0 GB13–20 tok/s32KUnified memory
Runs wellMistral-7B-Instruct-v0.1 Mistral AI7.2BBF16 (native)maker’s file15.2 / 24.0 GB13–20 tok/s32KUnified memory
Runs wellGemma 4 E2B Google5.1BBF16 (native)maker’s file10.1 / 24.0 GB20–30 tok/s125KUnified memory
Runs wellWeVisOne-VL-4B Tencent4.8BBF16 (native)maker’s file10.6 / 24.0 GB19–28 tok/s103KUnified memory
Runs wellQianfan-OCR Baidu4.7BBF16 (native)maker’s file10.5 / 24.0 GB19–29 tok/s31KUnified memory
Runs wellQwen3.5-4B Alibaba Qwen4.7BBF16 (native)maker’s file9.4 / 24.0 GB21–32 tok/s256KUnified memory
Runs wellQwen3-VL-4B-Instruct Alibaba Qwen4.4BBF16 (native)maker’s file9.9 / 24.0 GB20–30 tok/s108KUnified memory
Runs wellQwen3-4B-Instruct-2507 Alibaba Qwen4BBF16 (native)maker’s file9.1 / 24.0 GB22–33 tok/s114KUnified memory
Runs wellQwen3-4B Alibaba Qwen4BBF16 (native)maker’s file9.1 / 24.0 GB22–33 tok/s128KUnified memory
Runs wellDeepSeek-OCR DeepSeek3.3BBF16 (native)maker’s file7.2 / 24.0 GB74–110 tok/s8KUnified memory
Runs wellGranite-4.0-H-Micro IBM3.2BBF16 (native)maker’s file6.5 / 24.0 GB32–48 tok/s128KUnified memory
Runs wellQwen3-1.7B Alibaba Qwen2BBF16 (native)maker’s file5.2 / 24.0 GB41–61 tok/s40KUnified memory
Runs wellDeepSeek-R1-Distill-Qwen-1.5B DeepSeek1.8BBF16 (native)maker’s file4.0 / 24.0 GB54–81 tok/s125KUnified memory
Runs wellGLM-OCR Zhipu AI1.3BBF16 (native)maker’s file3.5 / 24.0 GB64–96 tok/s128KUnified memory
Runs wellQwen3-0.6B Alibaba Qwen0.8BBF16 (native)maker’s file2.8 / 24.0 GB84–126 tok/s40KUnified memory
Runs wellEmbeddingGemma 2 Google0.7BBF16 (native)maker’s file2.0 / 24.0 GB130–195 tok/s256KUnified memory
Runs wellQwen3-Embedding-0.6B Alibaba Qwen0.6BBF16 (native)maker’s file2.5 / 24.0 GB96–144 tok/s32KUnified memory
Runs wellbge-reranker-v2-m3 BAAI0.6BFP32 (native)maker’s file3.4 / 24.0 GB67–100 tok/s8KUnified memory
Runs wellbge-m3-unsupervised BAAI0.6BFP32 (native)maker’s file3.4 / 24.0 GB67–100 tok/s8KUnified memory
Runs wellbge-large-en-v1.5 BAAI0.3BFP32 (native)maker’s file1.8 / 24.0 GB147–221 tok/s512Unified memory
Runs wellbge-reranker-base BAAI0.3BFP32 (native)maker’s file1.6 / 24.0 GB181–272 tok/s514Unified memory
Runs wellbge-base-en-v1.5 BAAI0.1BFP32 (native)maker’s file0.9 / 24.0 GB449–673 tok/s512Unified memory
Runs wellbge-small-en-v1.5 BAAI0BFP32 (native)maker’s file0.6 / 24.0 GB1435–2152 tok/s512Unified memory
Runs, slowlyQwen2.5-VL-32B-Instruct Alibaba Qwen33.5BQ4_020.4 / 24.0 GB10–15 tok/s22KUnified memory
Runs, slowlyQwen3-VL-32B-Instruct Alibaba Qwen33.4BQ4_K_Mmaker’s file21.3 / 24.0 GB9–14 tok/s18KUnified memory
Runs, slowlyQwen3-VL-32B-Thinking Alibaba Qwen33.4BQ4_K_Mmaker’s file21.3 / 24.0 GB9–14 tok/s18KUnified memory
Runs, slowlyQwen2.5-32B-Instruct Alibaba Qwen32.8BQ4_K_Mmaker’s file21.4 / 24.0 GB9–14 tok/s18KUnified memory
Runs, slowlyQwen2.5-Coder-32B-Instruct Alibaba Qwen32.8BINT4 (AWQ / GPTQ)maker’s file20.9 / 24.0 GB10–14 tok/s20KUnified memory
Runs, slowlyQwQ-32B Alibaba Qwen32.8BQ4_K_Mmaker’s file21.4 / 24.0 GB9–14 tok/s18KUnified memory
Runs, slowlyDeepSeek-R1-Distill-Qwen-32B DeepSeek32.8BQ4_K_M21.5 / 24.0 GB9–14 tok/s18KUnified memory
Runs, slowlyQwen3-32B Alibaba Qwen32.8BQ4_K_Mmaker’s file21.3 / 24.0 GB9–14 tok/s18KUnified memory
Runs, slowlyGemma 4 31B IT Google31.3BQ4_K_M20.6 / 24.0 GB10–15 tok/s30KUnified memory
Runs, slowlyGranite Switch 4.1 30B IBM30BQ4_0maker’s file21.3 / 24.0 GB9–14 tok/s18KUnified memory

Estimates from the makers’ Hugging Face repositories (as of 2026-11-06); filtered views aren’t indexed. How it’s estimated