Hardware / Apple /Apple M5 Max (40-core GPU)

Apple · Apple Silicon

Apple M5 Max (40-core GPU)

for example MacBook Pro 14-inch and 16-inch. Memory is a build option on these, so not every one of them is sold with 128 GB.

Runs 163 models fully in memory, 2 more with CPU offload. 2 of those sit close enough to 128 GB that our size estimate is what decides them.

Memory

128 GB

Bandwidth

614 GB/s

Runs

163

01

Specifications

Memory

128 GB

Decides which models fit at all.

Memory bandwidth

614 GB/s

How fast it can read the model. Sets the speed of the reply.

Compute

46 TFLOPS

Trillions of half-precision sums a second. Sets how fast it reads a long prompt, not how fast it replies.

Power draw

70 W

At full load, for sizing a power supply.

Released

Mar 11, 2026

Architecture

M5

02

What it runs

Best quant per model. Text models first, then speech, then what does not fit.

What is quantisation? →

ModelParamsContextSpeedVerdict

Qwen3.6 35B A3B36B262K171 tok/sFits in memory Gemma 4 26B A4B25.8B262K128 tok/sFits in memory Nemotron 3 Nano 30B A3B31.6B262K171 tok/sFits in memory Ministral 3 3B 25123.8B131K159 tok/sFits in memory gpt-oss-safeguard-20b21.5B131K167 tok/sFits in memory Granite 4.0 Micro3.2B66K222 tok/sFits in memory Qwen3 VL 30B A3B Thinking31.1B262K201 tok/sFits in memory Qwen3 Next 80B A3B Thinking81.3B262K171 tok/sFits in memory gpt-oss-120b120B131K118 tok/sFits in memory Llama 3.2 3B Instruct3.2B131K189 tok/sFits in memory Qwen3.5-35B-A3B36B262K201 tok/sFits in memory Qwen3 VL 30B A3B Instruct31.1B262K171 tok/sFits in memory Qwen3 Next 80B A3B Instruct81.3B262K171 tok/sFits in memory Qwen3 30B A3B Thinking 250730.5B66K171 tok/sFits in memory Qwen3 Coder 30B A3B Instruct30.5B262K201 tok/sFits in memory Qwen3 30B A3B Instruct 250730.5B262K201 tok/sFits in memory Gemma 3 4B4.3B131K165 tok/sFits in memory Nemotron 3.5 Content Safety4.3B131K141 tok/sFits in memory Llama 3.2 1B Instruct1.2B33K504 tok/sFits in memory Qwen3 8B8.2B131K87 tok/sFits in memory Llama 3.1 8B Instruct8B131K89 tok/sFits in memory UI-TARS 7B8.3B66K85 tok/sFits in memory Hy-MT2-1.8B2B8K301 tok/sFits in memory Hy-MT2-30B-A3B30.1B8K171 tok/sFits in memory Granite 4.1 8B8.8B131K81 tok/sFits in memory Ministral 3 8B 25128.9B262K80 tok/sFits in memory Qwen3 VL 8B Thinking8.8B131K81 tok/sFits in memory Gemma 3n 4B7.8B33K91 tok/sFits in memory Qwen3 VL 8B Instruct8.8B262K81 tok/sFits in memory Qwen2.5 7B Instruct7.6B33K93 tok/sFits in memory Granite 4.2 8B8.8B131K81 tok/sFits in memory Reka Edge7.1B16K100 tok/sFits in memory Qwen3.5-9B9.7B262K73 tok/sFits in memory Qwen3.5-122B-A10B125B131K60 tok/sFits in memory Llama Guard 4 12B12B262K59 tok/sFits in memory Gemma 3 12B12.2B131K58 tok/sFits in memory Rocinante 12B12.2B66K58 tok/sFits in memory Mistral Nemo12.2B131K58 tok/sFits in memory Ministral 3 14B 251213.9B262K51 tok/sFits in memory GLM 4.5 Air111B66K50 tok/sFits in memory Llama 3 8B Lunaris8B8K89 tok/sFits in memory Hunyuan A13B Instruct80.4B131K46 tok/sFits in memory Qwen3 14B14.8B131K48 tok/sFits in memory UnslopNemo 12B12.2B33K58 tok/sFits in memory Hy-MT2-7B8B8K75 tok/sFits in memory Cydonia 24B V4.123.6B131K30 tok/sFits in memory Reka Flash 320.9B66K34 tok/sFits in memory Uncensored24B66K30 tok/sFits in memory Mistral Small 3.2 24B24B131K30 tok/sFits in memory Mistral Small 3.1 24B24B66K30 tok/sFits in memory Ternary Bonsai 2 27B27B262K26 tok/sFits in memory Gemma 4 31B31.3B66K23 tok/sFits in memory Qwen3.5-27B27.8B262K26 tok/sFits in memory Olmo 3 32B Think32.2B66K22 tok/sFits in memory Gemma 3 27B27.4B262K26 tok/sFits in memory Phi 414.7B16K48 tok/sFits in memory Qwen3.6 27B27.8B262K26 tok/sFits in memory Muse Glimmer 30B29.8B131K24 tok/sFits in memory Qwen3.8 27B27.8B262K26 tok/sFits in memory GLM 4.7 Flash31.2B131K19 tok/sFits in memory Qwen3 VL 32B Instruct33.4B131K21 tok/sFits in memory MythoMax 13B13B8K55 tok/sFits in memory Laguna XS 2.133.4B262K18 tok/sFits in memory Qwen3 32B32.8B131K22 tok/sFits in memory Mistral Small 323.6B33K30 tok/sFits in memory Nemotron 3.5 Lightning31.6B262K19 tok/sFits in memory Nex-N2-Mini35.1B262K17 tok/sFits in memory Nex-N2.5-Mini35.1B262K15 tok/sFits in memory Hermes 4 70B70.6B131K10 tok/sFits in memory Llama 3.3 Euryale 70B70.6B131K10 tok/sFits in memory Llama 3.1 Euryale 70B v2.270.6B131K10 tok/sFits in memory Hermes 3 70B Instruct70.6B131K10 tok/sFits in memory Llama 3.1 70B Instruct70.6B131K10 tok/sFits in memory Llama 3.3 70B Instruct70.6B131K10 tok/sFits in memory Qwen3 Coder Next79.7B262K6 tok/sFits in memory Command A111B66K6 tok/sFits in memory Skyfall 36B V236.9B33K19 tok/sFits in memory Qwen2.5 VL 72B Instruct73.4B66K10 tok/sFits in memory Qwen2.5 Coder 32B Instruct32.8B33K18 tok/sFits in memory ReMM SLERP 13B13B4K55 tok/sFits in memory Llama 4 Scout109B66K7 tok/sFits in memory Nemotron 3 Super124B131K5 tok/sFits in memory GLM 4.6V108B66K5 tok/sFits in memory Voxtral Small 24B 250724.3B16K29 tok/sFits in memory GLM 4.5V108B66K6 tok/sFits in memory Qwen2.5 72B Instruct72.7B33K10 tok/sFits in memory Mistral Medium 3.5128B33K6 tok/sFits in memory Ling-2.6-flash107B33K6 tok/sFits in memory Devstral 2 2512125B33K6 tok/sFits in memory Gemma 2 27B27.2B8K26 tok/sFits in memory Magnum v4 72B72.7B16K8 tok/sFits in memory Laguna S 2.1118B16K4 tok/sFits in memoryest Mistral Small 4119B16K5 tok/sFits in memory Mixtral 8x22B Instruct141B8K16 tok/sFits in memoryest Ling-3.0-flash128B16K5 tok/sFits in memory R1 Distill Llama 70B70.6B8K10 tok/sFits in memory

Speech models it runs67 modelsTranscription and speech models that fit in memory. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.

Niagara 19m Batch.en20M20226 tok/sFits in memory Niagara 38m Batch.en38M10645 tok/sFits in memory Higgs Audio v3 STT2.7B150 tok/sFits in memory Cohere Transcribe 03 20262.1B193 tok/sFits in memory Distil Large v3.50.8B506 tok/sFits in memory Lite Whisper Large v3 Acc1.4B432 tok/sFits in memory Owsm CTC v3.1 1B1.1B645 tok/sFits in memory Owsm CTC v3.2 ft 1B1B405 tok/sFits in memory Owsm CTC v4 1B1B709 tok/sFits in memory Hubert Large Ls960 ft0.3B1264 tok/sFits in memory MMS 1b All1B604 tok/sFits in memory Wav2vec2 Large 960h Lv60 Self0.3B1264 tok/sFits in memory Hojo ASR V15.2B137 tok/sFits in memory Granite 4.0 1b Speech2.3B176 tok/sFits in memory Granite Speech 3.3 2b3B236 tok/sFits in memory Granite Speech 4.1 2b2.3B308 tok/sFits in memory Granite Speech 4.1 2b NAR2.3B308 tok/sFits in memory STT 2.6b en2.6B273 tok/sFits in memory Phi 4 Multimodal Instruct5.6B131K127 tok/sFits in memory Voxtral Mini 3B 25074.7B129 tok/sFits in memory Voxtral Mini 4B Realtime 26024.4B137 tok/sFits in memory Canary 180m Flash0.2B3357 tok/sFits in memory Canary 1b1B405 tok/sFits in memory Canary 1b Flash0.8B506 tok/sFits in memory Canary 1b v21B405 tok/sFits in memory Canary Qwen 2.5b2.6B156 tok/sFits in memory Nemotron 3.5 ASR Streaming 0.6b0.6B674 tok/sFits in memory Nemotron Speech Streaming en 0.6b0.6B674 tok/sFits in memory Parakeet CTC 0.6b0.6B1182 tok/sFits in memory Parakeet CTC 1.1b1.1B368 tok/sFits in memory Parakeet RNNT 0.6b0.6B674 tok/sFits in memory Parakeet RNNT 1.1b1.1B645 tok/sFits in memory Parakeet TDT CTC 110m0.1B3677 tok/sFits in memory Parakeet TDT 0.6b v20.6B1007 tok/sFits in memory Parakeet TDT 0.6b v30.6B674 tok/sFits in memory Parakeet TDT 1.1b1.1B368 tok/sFits in memory Nyra Health CrisperWhisper1.6B253 tok/sFits in memory Whisper Large v31.5B403 tok/sFits in memory Whisper Large v3 Turbo0.8B886 tok/sFits in memory MOSS Transcribe Diarize0.9B450 tok/sFits in memory Qwen3 ASR 0.6B0.9B788 tok/sFits in memory Qwen3 ASR 0.6B HF0.8B886 tok/sFits in memory Qwen3 ASR 1.7B2.3B263 tok/sFits in memory Qwen3 ASR 1.7B HF2B202 tok/sFits in memory Zipformer cr CTC Transducer XL 290M0.3B2084 tok/sFits in memory Zipformer Transducer XL 290M0.3B1395 tok/sFits in memory ASR Conformer Largescaleasr0.5B1477 tok/sFits in memory GLM ASR Nano 25122.3B263 tok/sFits in memory Granite Speech 5.0 470m Turboctc0.5B1418 tok/sFits in memory Granite Speech 5.0 470m Turboctc nc0.5B1209 tok/sFits in memory Fun ASR Nano 2512 HF0.8B886 tok/sFits in memory Gemma 4 E2B it5.1B139 tok/sFits in memory Niagara 9m Batch.en9M44946 tok/sFits in memory Niagara 84m Batch.en84M4816 tok/sFits in memory ARK ASR 0.6B1.3B33K545 tok/sFits in memory ARK ASR 3B4.1B33K173 tok/sFits in memory Audio8 ASR 0.1B0.3B33K1348 tok/sFits in memory MOSS Transcribe Preview 2B2.4B33K295 tok/sFits in memory Gemma 4 E4B it8B131K89 tok/sFits in memory Granite Speech 3.3 8b8.6B82 tok/sFits in memory VibeVoice ASR HF8.3B85 tok/sFits in memory Higgs Audio v3 8b STT v28.9B80 tok/sFits in memory Moonshine Streaming Medium0.3B4K2363 tok/sFits in memory Moonshine Streaming Small0.1B4K4045 tok/sFits in memory Gemma 4 12B it12B59 tok/sFits in memory Moonshine Streaming Tiny0B4Kno speed estimateFits in memory Moonshine Tiny0B194no speed estimateFits in memory

Runs only by spilling into system memory2 modelsThese load, but part of the weights sits in ordinary system memory, which is far slower than the chip.

Step 3.7 Flash201B—no speed estimateSpills to system RAMest Step 3.5 Flash199B—no speed estimateSpills to system RAMest

Too large for this device59 modelsThe weights do not fit even with part of them offloaded to system memory. Closest calls first.

MiniMax M2.7229B—no speed estimateToo largeest Qwen3 VL 235B A22B Instruct236B—no speed estimateToo largeest MiniMax M2.5229B—no speed estimateToo large Qwen3 235B A22B Instruct 2507235B—no speed estimateToo large Qwen3 VL 235B A22B Thinking236B—no speed estimateToo large DeepSeek V4 Flash291B—no speed estimateToo large GLM 5.3 Flash321B—no speed estimateToo large Laguna M.1226B—no speed estimateToo large Nex-N2-Pro397B—no speed estimateToo large Trinity Large Thinking399B—no speed estimateToo large MiniMax M2.1229B—no speed estimateToo large MiniMax M2229B—no speed estimateToo large Hermes 4 405B406B—no speed estimateToo large Hermes 3 405B Instruct406B—no speed estimateToo large Qwen3 235B A22B Thinking 2507235B—no speed estimateToo large GLM 4.6357B—no speed estimateToo large GLM 4.7358B—no speed estimateToo large MiniMax M3427B—no speed estimateToo large Nex-N2.5-Pro397B—no speed estimateToo large Inkling Small266B—no speed estimateToo large Llama 4 Maverick402B—no speed estimateToo large Qwen3 Coder 480B A35B480B—no speed estimateToo large ERNIE 4.5 VL 424B A47B424B—no speed estimateToo large Hy3299B—no speed estimateToo large Hy3 preview299B—no speed estimateToo large DeepSeek V4 Flash Vision Exp305B—no speed estimateToo large MiniMax-01456B—no speed estimateToo large MiMo-V2.5311B—no speed estimateToo large GLM 4.5358B—no speed estimateToo large Nemotron 3 Ultra561B—no speed estimateToo large Jamba Large 1.7399B—no speed estimateToo large Qwen3.5 397B A17B403B—no speed estimateToo large GLM 5.1754B—no speed estimateToo large GLM 5.2753B—no speed estimateToo large MiniMax M1456B—no speed estimateToo large DeepSeek V3.1 Terminus685B—no speed estimateToo large DeepSeek V3685B—no speed estimateToo large GLM 5754B—no speed estimateToo large Kimi K2 07111T—no speed estimateToo large Ling-2.6-1T1T—no speed estimateToo large Inkling952B—no speed estimateToo large R1 0528685B—no speed estimateToo large DeepSeek V3 0324685B—no speed estimateToo large DeepSeek V3.1685B—no speed estimateToo large DeepSeek V3.2685B—no speed estimateToo large DeepSeek V3.2 Exp685B—no speed estimateToo large Kimi K2 09051T—no speed estimateToo large Ring-2.6-1T1T—no speed estimateToo large Kimi K2.7 Code1.1T—no speed estimateToo large Kimi K2.61.1T—no speed estimateToo large DeepSeek V4.1 Flash763B—no speed estimateToo large Hy4 preview780B—no speed estimateToo large MiMo-V2.5-Pro1T—no speed estimateToo large Kimi K2 Thinking1.1T—no speed estimateToo large Kimi K2.51.1T—no speed estimateToo large DeepSeek V4 Pro1.6T—no speed estimateToo large Qwen3.8 2.4T A95B2.4T—no speed estimateToo large LongCat 2.01.8T—no speed estimateToo large Kimi K32.8T—no speed estimateToo large

224 models have a verdict on this device: 163 fit in memory, 2 spill into system memory and 59 are too large. Every one of them is on this page.

03

Other M5 chips

The same generation in other memory sizes. Memory is what decides which models fit.

Apple M5 (10-core GPU)32 GB · less memory Apple M5 Max (32-core GPU)64 GB · less memory Apple M5 Pro (20-core GPU)64 GB · less memory

Something wrong on this page? Tell us