Hardware / Apple /Apple M1 Max (32-core GPU)

Apple · Apple Silicon

Apple M1 Max (32-core GPU)

for example MacBook Pro 14-inch and 16-inch (2021), Mac Studio (2022)

Runs 123 models fully in memory, 10 more with CPU offload. 7 of those sit close enough to 64 GB that our size estimate is what decides them.

Memory

64 GB

Bandwidth

400 GB/s

Runs

123

01

Specifications

Memory

64 GB

Bandwidth

400 GB/s

FP16 compute

21.2 TFLOPS

TDP

60 W

MSRP

—

Street price

—

Released

Oct 26, 2021

Architecture

M1

02

What it runs

Best quant per model — sorted by fit score.

ModelParamsBest quantContextSpeedVerdict

Qwen3.6 35B A3B36BQ4_K_M262K131 tok/sestFits in memory Nemotron 3 Nano 30B A3B31.6BQ4_K_M262K131 tok/sestFits in memory Ministral 3 3B 25123.8BQ4_K_M131K122 tok/sestFits in memory Granite 4.0 Micro3.2BQ4_K_M66K123 tok/sestFits in memory Qwen3 VL 30B A3B Thinking31.1BQ4_K_M262K131 tok/sestFits in memory Llama 3.2 3B Instruct3.2BQ5_K_M131K123 tok/sestFits in memory Qwen3.5-35B-A3B36BQ4_K_M262K131 tok/sestFits in memory Qwen3 VL 30B A3B Instruct31.1BQ4_K_M262K131 tok/sestFits in memory Qwen3 30B A3B Thinking 250730.5BQ4_K_M66K131 tok/sestFits in memory Qwen3 Coder 30B A3B Instruct30.5BQ4_K_M262K131 tok/sestFits in memory Qwen3 30B A3B Instruct 250730.5BQ4_K_M262K131 tok/sestFits in memory Niagara 19m Batch.en20MQ8_0~262K13177 tok/sestFits in memory Niagara 38m Batch.en38MQ8_0~262K6935 tok/sestFits in memory ARK ASR 0.6B1.3BQ8_0~262K203 tok/sestFits in memory Audio8 ASR 0.1B0.3BQ5_K_M~262K1312 tok/sestFits in memory Higgs Audio v3 STT2.7BQ4_K_M~262K171 tok/sestFits in memory Cohere Transcribe 03 20262.1BQ4_K_M~262K220 tok/sestFits in memory Distil Large v3.50.8BQ5_K_M~262K492 tok/sestFits in memory Lite Whisper Large v3 Acc1.4BQ8_0~262K188 tok/sestFits in memory Owsm CTC v3.1 1B1.1BQ5_K_M~262K358 tok/sestFits in memory Owsm CTC v3.2 ft 1B1BQ4_K_M~262K462 tok/sestFits in memory Owsm CTC v4 1B1BQ4_K_M~262K462 tok/sestFits in memory Hubert Large Ls960 ft0.3BQ4_K_M~262K1443 tok/sestFits in memory MMS 1b All1BQ4_K_M~262K462 tok/sestFits in memory Wav2vec2 Large 960h Lv60 Self0.3BQ5_K_M~262K1230 tok/sestFits in memory Granite 4.0 1b Speech2.3BQ5_K_M~262K171 tok/sestFits in memory Granite Speech 3.3 2b3BQ5_K_M~262K131 tok/sestFits in memory Granite Speech 4.1 2b2.3BQ5_K_M~262K171 tok/sestFits in memory Granite Speech 4.1 2b NAR2.3BQ4_K_M~262K201 tok/sestFits in memory STT 2.6b en2.6BQ5_K_M~262K151 tok/sestFits in memory Canary 180m Flash0.2BQ4_K_M~262K2566 tok/sestFits in memory Canary 1b1BQ5_K_M~262K394 tok/sestFits in memory Canary 1b Flash1BQ5_K_M~262K394 tok/sestFits in memory Canary 1b v21BQ4_K_M~262K462 tok/sestFits in memory Canary Qwen 2.5b2.6BQ4_K_M~262K178 tok/sestFits in memory Nemotron 3.5 ASR Streaming 0.6b0.6BQ8_0~262K412 tok/sestFits in memory Nemotron Speech Streaming en 0.6b0.6BQ4_K_M~262K770 tok/sestFits in memory Parakeet CTC 0.6b0.6BQ5_K_M~262K656 tok/sestFits in memory Parakeet CTC 1.1b1.1BQ5_K_M~262K358 tok/sestFits in memory Parakeet RNNT 0.6b0.6BQ8_0~262K439 tok/sestFits in memory Parakeet RNNT 1.1b1.1BQ8_0~262K240 tok/sestFits in memory Parakeet TDT CTC 110m0.1BQ8_0~262K2396 tok/sestFits in memory Parakeet TDT 0.6b v20.6BQ5_K_M~262K656 tok/sestFits in memory Parakeet TDT 0.6b v30.6BQ5_K_M~262K656 tok/sestFits in memory Parakeet TDT 1.1b1.1BQ5_K_M~262K358 tok/sestFits in memory Nyra Health CrisperWhisper1.6BQ5_K_M~262K246 tok/sestFits in memory Whisper Large v31.5BQ5_K_M~262K262 tok/sestFits in memory Whisper Large v3 Turbo0.8BQ5_K_M~262K492 tok/sestFits in memory MOSS Transcribe Diarize0.9BQ8_0~262K293 tok/sestFits in memory MOSS Transcribe Preview 2B2.4BQ5_K_M~66K164 tok/sestFits in memory Qwen3 ASR 0.6B0.8BQ5_K_M~262K505 tok/sestFits in memory Qwen3 ASR 0.6B HF0.8BQ5_K_M~262K492 tok/sestFits in memory Qwen3 ASR 1.7B2BQ4_K_M~262K226 tok/sestFits in memory Qwen3 ASR 1.7B HF2BQ5_K_M~262K193 tok/sestFits in memory Zipformer cr CTC Transducer XL 290M0.3BQ8_0~262K909 tok/sestFits in memory Zipformer Transducer XL 290M0.3BQ5_K_M~262K1358 tok/sestFits in memory ASR Conformer Largescaleasr0.5BQ4_K_M~262K962 tok/sestFits in memory Moonshine Streaming Medium0.2BQ4_K_M~262K1924 tok/sestFits in memory Moonshine Streaming Small0.1BQ8_0~262K2635 tok/sestFits in memory Moonshine Streaming Tiny30MQ4_K_M~262K15395 tok/sestFits in memory

A speed marked est is calculated from this card's memory bandwidth and the size of the weights it has to read per word. It is not a measurement.

Something wrong on this page? Tell us