Apple Mac Studio (2025) (M4 Max or M3 Ultra)

Configurations

Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.

Specifications 96.0 GB configuration

Best LLMs for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 96.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A+92Excellent quality (A+) · 92 of 100: how capable the model is at F16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 26B-A4BGoogle	F16	58.4 GB	43.3 tok/s	Runs great
A+93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.6 35B-A3BAlibaba	Q8_0	44.6 GB	94.2 tok/s	Runs great
A+93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 35B-A3BAlibaba	Q8_0	44.6 GB	94.2 tok/s	Runs great
A+93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	OBMiniCPM-V 4.7 35B-A3BOpenBMB	Q8_0	43.9 GB	94.2 tok/s	Runs great
A+90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	RFlint (40B-A2.5B)Recursive	Q8_0	48.8 GB	106 tok/s	Runs great
A+92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	NANex N2 Mini (35B-A3B)Nex-AGI	Q8_0	43.7 GB	94.2 tok/s	Runs great
A+89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3.5 Bolt 74B-A9BNVIDIA	Q5_K_M	59.6 GB	62.2 tok/s	Runs great
A+91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	ISSage-A1.5 35B-A3BInternScience	Q8_0	44.6 GB	94.2 tok/s	Runs great
A+91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	KKAT-Coder V2.5 Dev (35B-A3B)Kuaishou	Q8_0	43.3 GB	94.2 tok/s	Runs great
A+90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	DROrnith 1.5 35B-A3BDeepReinforce	Q8_0	44.6 GB	94.2 tok/s	Runs great

Best Image models for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 96.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A+92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	KKrea 2 TurboKrea	FP16	37.4 GB	18 s	Runs well
A84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX.2 [klein] 9BBlack Forest Labs	FP16	37.1 GB	7.6 s	Runs great
A+89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Qwen-Image 2.1 TurboAlibaba	FP16	46.7 GB	49 s	Slow
A+92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	IIdeogram 4Ideogram	FP16	57.3 GB	1.8 min	Slow
A+93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	Qwen-Image 2.1Alibaba	FP16	57.0 GB	4.2 min	Very slow
A84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	FP16	22.7 GB	11 s	Runs great

Best Video models for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 96.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A+86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-2.5 (22B, video + audio)Lightricks	FP8	48.3 GB	5.8 min	Runs well
A84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-2.3Lightricks	FP8	44.3 GB	25.4 min	Slow
A+85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	BDBernini-R A14B (video generation + editing)ByteDance	FP16	46.0 GB	50.8 min	Very slow
A+86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.2 I2V A14BAlibaba	FP16	58.0 GB	1.9 h	Very slow
A+86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.2 T2V A14BAlibaba	FP16	58.0 GB	1.9 h	Very slow

Best Decision models for the Apple Mac Studio (2025) (M4 Max or M3 Ultra) 96.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A+86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	JAJina Reranker v3.5Jina AI	F16	7.8 GB	24 ms	Runs great
A+90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 4BAlibaba	Q8_0	10.9 GB	130 ms	Runs great
A84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	SAIntern-Decision 4BShanghai AI Lab	F16	15.5 GB	92 ms	Runs great
A84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	JAJina Reranker v3Jina AI	F16	7.8 GB	24 ms	Runs great
A+88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	ZEzerank-2ZeroEntropy	Q8_0	10.9 GB	130 ms	Runs great
A+86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Shieldstral 1.0 3BMistral AI	Q8_0	10.7 GB	125 ms	Runs great
A82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	LAd1 3BLiquid AI	F16	12.6 GB	65 ms	Runs great
A82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	Mmxbai-rerank-large v2Mixedbread	F16	9.5 GB	56 ms	Runs great