Which local LLMs can the Apple M4 Pro (Mac mini, MacBook Pro) run?

Unified memory — by default the GPU can use about 70% of it

Assumes 8k context and an f16 KV cache. Verdicts are shown for each memory size.

What to expect from the Apple M4 Pro

The M4 Pro comes with 24GB, 48GB or 64GB of unified memory at 273 GB/s, more than twice the bandwidth of the Apple M4. Even the 24GB configuration runs gpt-oss-20b and Llama 3.1 8B great, and Qwen3 14B runs well. Our page for gpt-oss-20b on the Apple M4 Pro has the run commands.

With 48GB, mixture-of-experts models such as Qwen3 30B-A3B, Qwen3.5 35B-A3B and Gemma 4 26B-A4B load completely and run great. On 24GB, Qwen3 30B-A3B falls back to the CPU and Qwen3.5 35B-A3B does not load. Dense models are much slower, because every token reads all of their weights. At 48GB, Gemma 3 27B runs well, and Gemma 4 31B runs slowly: its thinking mode is off by default, but CanRun still holds models that have one to a 1.5× stricter speed bar.

64GB adds room rather than speed. Llama 3.3 70B fits in its IQ4_XS file and runs slowly, and gpt-oss-120b, at 64.3 GB, does not fit at all. That one needs more unified memory than any M4 Pro has, such as the 128GB Apple M4 Max (40-core GPU).

Specs

Memory options: 24 GB · 48 GB · 64 GB
Memory bandwidth: 273.0 GB/s
FP16 compute: 8.1 TFLOPS
Launch year: 2024
Macs with this chip: Mac mini: 24 GB · 48 GB · 64 GB
MacBook Pro: 24 GB · 48 GB
Also written as: M4 Pro

Verdicts at a glance

At Q4_K_M (or the closest available quant) with 8k context.

24 GBRuns great24 modelsRuns well6 modelsRuns slowly10 modelsWon't run19 models8 more models run at a lower quant.
48 GBRuns great31 modelsRuns well7 modelsRuns slowly11 modelsWon't run10 models4 more models run at a lower quant.
64 GBRuns great31 modelsRuns well7 modelsRuns slowly13 modelsWon't run8 models2 more models run at a lower quant.

How to read the verdicts

Runs great: Fully on the GPU at 20 tok/s or more
Runs well: Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
Runs slowly: 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
Won't run: Does not fit, or under 2 tok/s

Every model on the Apple M4 Pro

Scroll sideways to see every column.

59 models sorted by verdict and speed, with 64 GB of memory
Model	Verdict	Speed	Quant	Memory	Runs as	Context	Notes
MiniCPM5 1B	Runs great	est. 232.8 tok/s186.2–279.3calibrated estimate ±20%	Q4_K_M	1.5 / 44.8 GB	Unified memory	up to 128k	thinking mode
Llama 3.2 1B	Runs great	est. 192.4 tok/s153.9–230.9calibrated estimate ±20%	Q4_K_M	1.7 / 44.8 GB	Unified memory	up to 128k	—
Ling-3.0 Tiny	Runs great	est. 175.4 tok/s122.8–228.1theoretical estimate ±30%	Q4_K_M	5.5 / 44.8 GB	Unified memory	up to 128k	thinking mode
EXAONE 4.0 1.2B	Runs great	est. 158.0 tok/s126.4–189.6calibrated estimate ±20%	Q4_K_M	1.9 / 44.8 GB	Unified memory	up to 64k	thinking mode
LFM2.5 2.6B	Runs great	est. 115.0 tok/s80.5–149.5theoretical estimate ±30%	Q4_K_M	2.4 / 44.8 GB	Unified memory	up to 128k	thinking mode
HyperCLOVA X SEED 1.5B	Runs great	est. 114.3 tok/s91.4–137.2calibrated estimate ±20%	Q4_K_M	2.4 / 44.8 GB	Unified memory	up to 16k	—
MiniCPM5 2B	Runs great	est. 108.5 tok/s86.8–130.2calibrated estimate ±20%	Q4_K_M	2.5 / 44.8 GB	Unified memory	up to 64k	thinking mode
Gemma 4 E2B	Runs great	est. 108.4 tok/s75.9–141.0theoretical estimate ±30%	Q4_K_M	3.7 / 44.8 GB	Unified memory	up to 128k	thinking mode
Mellum2.1 12B-A2.5B Thinking	Runs great	est. 101.8 tok/s81.4–122.2calibrated estimate ±20%	Q4_K_M	8.8 / 44.8 GB	Unified memory	up to 128k	thinking mode
MiniCPM-V 4.7 35B-A3B	Runs great	est. 74.2 tok/s59.3–89.0calibrated estimate ±20%	Q4_K_M	21.9 / 44.8 GB	Unified memory	up to 128k	thinking mode
Spark-X2.5 4B	Runs great	est. 71.5 tok/s57.2–85.8calibrated estimate ±20%	Q4_K_M	3.5 / 44.8 GB	Unified memory	up to 64k	thinking mode
Llama 3.2 3B	Runs great	est. 70.1 tok/s56.1–84.1calibrated estimate ±20%	Q4_K_M	3.5 / 44.8 GB	Unified memory	up to 64k	—
gpt-oss-20b	Runs greatgpt-oss-20b verdict on the Apple M4 Pro	est. 69.9 tok/s55.9–83.9calibrated estimate ±20%	MXFP4	12.9 / 44.8 GB	Unified memory	up to 128k	thinking mode
Qwen3.6 35B-A3B	Runs greatQwen3.6 35B-A3B verdict on the Apple M4 Pro	est. 68.8 tok/s55.0–82.5calibrated estimate ±20%	Q4_K_M	23.0 / 44.8 GB	Unified memory	up to 128k	thinking mode
Nemotron 3.5 Lightning 30B-A3B	Runs great	est. 68.0 tok/s47.6–88.4theoretical estimate ±30%	Q4_K_M	26.1 / 44.8 GB	Unified memory	up to 256k	thinking mode
Qwen3.5 4B	Runs great	est. 67.0 tok/s53.6–80.4calibrated estimate ±20%	Q4_K_M	3.7 / 44.8 GB	Unified memory	up to 64k	thinking mode
Kanana 1.5 15.7B-A3B	Runs great	est. 60.6 tok/s48.5–72.8calibrated estimate ±20%	Q4_K_M	12.1 / 44.8 GB	Unified memory	up to 32k	—
Qwen3.5 35B-A3B	Runs greatQwen3.5 35B-A3B verdict on the Apple M4 Pro	est. 60.3 tok/s48.3–72.4calibrated estimate ±20%	Q4_K_M	23.4 / 44.8 GB	Unified memory	up to 128k	thinking mode
Qwen3 30B-A3B (2507)	Runs greatQwen3 30B-A3B (2507) verdict on the Apple M4 Pro	est. 59.2 tok/s47.4–71.1calibrated estimate ±20%	Q4_K_M	19.9 / 44.8 GB	Unified memory	up to 64k	—
Gemma 4 E4B	Runs great	est. 58.7 tok/s41.1–76.3theoretical estimate ±30%	Q4_K_M	5.7 / 44.8 GB	Unified memory	up to 128k	thinking mode
Gemma 4 26B-A4B	Runs greatGemma 4 26B-A4B verdict on the Apple M4 Pro	est. 50.2 tok/s40.2–60.2calibrated estimate ±20%	Q4_K_M	17.7 / 44.8 GB	Unified memory	up to 128k	thinking mode
Qwen3.5 9B	Runs greatQwen3.5 9B verdict on the Apple M4 Pro	37.0 tok/s8k estimate 33.8 tok/s (27.0–40.6, calibrated estimate ±20%)measured (1 run, 4k context)	Q4_K_M	6.7 / 44.8 GB	Unified memory	up to 16k	thinking mode
K2-Horizon MoVA 36B-A4B	Runs great	est. 36.8 tok/s25.8–47.8theoretical estimate ±30%	Q4_K_M	24.6 / 44.8 GB	Unified memory	up to 8k	thinking mode
DeepSeek R1 Distill Llama 8B	Runs great	est. 34.6 tok/s27.7–41.5calibrated estimate ±20%	Q4_K_M	6.6 / 44.8 GB	Unified memory	up to 8k	thinking mode
Kanana 1.5 8B	Runs great	est. 34.6 tok/s27.7–41.5calibrated estimate ±20%	Q4_K_M	6.6 / 44.8 GB	Unified memory	up to 32k	—
Llama 3.1 8B	Runs greatLlama 3.1 8B verdict on the Apple M4 Pro	est. 34.6 tok/s27.7–41.5calibrated estimate ±20%	Q4_K_M	6.6 / 44.8 GB	Unified memory	up to 32k	—
Nanbeige4.2 3B	Runs great	est. 33.9 tok/s23.7–44.0theoretical estimate ±30%	Q4_K_M	4.7 / 44.8 GB	Unified memory	up to 8k	thinking mode
DeepSeek R1 0528 Qwen3 8B	Runs great	est. 33.3 tok/s26.6–39.9calibrated estimate ±20%	Q4_K_M	6.8 / 44.8 GB	Unified memory	up to 8k	thinking mode
Qwen3 8B	Runs greatQwen3 8B verdict on the Apple M4 Pro	est. 33.3 tok/s26.6–39.9calibrated estimate ±20%	Q4_K_M	6.8 / 44.8 GB	Unified memory	up to 8k	thinking mode
K2-Horizon 7B	Runs great	est. 30.5 tok/s24.4–36.6calibrated estimate ±20%	Q4_K_M	7.4 / 44.8 GB	Unified memory	up to 8k	thinking mode
Gemma 3 12B	Runs greatGemma 3 12B verdict on the Apple M4 Pro	est. 26.5 tok/s21.2–31.8calibrated estimate ±20%	Q4_K_M	8.4 / 44.8 GB	Unified memory	up to 32k	—
Gemma 4 12B	Runs wellGemma 4 12B verdict on the Apple M4 Pro	est. 28.6 tok/s22.9–34.3calibrated estimate ±20%	Q4_K_M	7.8 / 44.8 GB	Unified memory	up to 256k	Try IQ4_XS: Runs great thinking mode
HyperCLOVA X SEED Think 14B	Runs well	est. 20.4 tok/s14.2–26.5theoretical estimate ±30%	Q4_K_M	10.8 / 44.8 GB	Unified memory	up to 32k	thinking mode
Qwen3 14B	Runs wellQwen3 14B verdict on the Apple M4 Pro	est. 20.1 tok/s16.0–24.1calibrated estimate ±20%	Q4_K_M	10.9 / 44.8 GB	Unified memory	up to 32k	thinking mode
DeepSeek R1 Distill Qwen 14B	Runs well	est. 19.6 tok/s15.7–23.5calibrated estimate ±20%	Q4_K_M	11.2 / 44.8 GB	Unified memory	up to 32k	thinking mode
Phi-4	Runs well	est. 19.3 tok/s15.5–23.2calibrated estimate ±20%	Q4_K_M	11.3 / 44.8 GB	Unified memory	up to 16k	—
Mistral Small 3.2 24B	Runs well	est. 13.2 tok/s10.6–15.9calibrated estimate ±20%	Q4_K_M	16.2 / 44.8 GB	Unified memory	up to 64k	Q2_K (heavy quality loss): Runs great
Gemma 3 27B	Runs well	est. 12.0 tok/s9.6–14.5calibrated estimate ±20%	Q4_K_M	17.8 / 44.8 GB	Unified memory	up to 64k	—
Kolibri 1	Runs slowly	est. 49.5 tok/s34.6–64.3theoretical estimate ±30%	Q4_K_M	49.9 GB RAM	CPU only	up to 256k	CPU inference — capped at Runs slowly Try IQ4_XS: Runs great thinking mode
Qwen3.6 27B	Runs slowly	est. 12.0 tok/s9.6–14.3calibrated estimate ±20%	Q4_K_M	17.9 / 44.8 GB	Unified memory	up to 256k	Try IQ4_XS: Runs well thinking mode
Muse Glimmer 30B	Runs slowly	est. 11.9 tok/s9.5–14.3calibrated estimate ±20%	Q4_K_M	18.0 / 44.8 GB	Unified memory	up to 128k	Try IQ4_XS: Runs well thinking mode
Qwen3.8 27B	Runs slowlyQwen3.8 27B verdict on the Apple M4 Pro	est. 11.5 tok/s9.2–13.8calibrated estimate ±20%	Q4_K_M	18.6 / 44.8 GB	Unified memory	up to 256k	Try IQ4_XS: Runs well thinking mode
Gemma 4 31B	Runs slowlyGemma 4 31B verdict on the Apple M4 Pro	est. 10.9 tok/s8.7–13.1calibrated estimate ±20%	Q4_K_M	19.6 / 44.8 GB	Unified memory	up to 256k	Try IQ4_XS: Runs well thinking mode
Granite 4.2 30B	Runs slowly	est. 10.4 tok/s8.4–12.5calibrated estimate ±20%	Q4_K_M	20.4 / 44.8 GB	Unified memory	up to 64k	Q2_K (heavy quality loss): Runs well thinking mode
EXAONE 4.0 32B	Runs slowly	est. 10.4 tok/s8.4–12.5calibrated estimate ±20%	Q4_K_M	20.5 / 44.8 GB	Unified memory	up to 128k	thinking mode
EXAONE 4.5 33B	Runs slowly	est. 10.1 tok/s8.1–12.1calibrated estimate ±20%	Q4_K_M	21.2 / 44.8 GB	Unified memory	up to 256k	thinking mode
Qwen3.5 27B	Runs slowlyQwen3.5 27B verdict on the Apple M4 Pro	9.9 tok/s8k estimate 11.8 tok/s (9.4–14.1, calibrated estimate ±20%)measured (1 run, 512 context)	Q4_K_M	18.2 / 44.8 GB	Unified memory	up to 256k	Try IQ4_XS: Runs well thinking mode
Qwen3 32B	Runs slowlyQwen3 32B verdict on the Apple M4 Pro	est. 9.5 tok/s7.6–11.4calibrated estimate ±20%	Q4_K_M	22.5 / 44.8 GB	Unified memory	up to 32k	Q2_K (heavy quality loss): Runs well thinking mode
DeepSeek R1 Distill Qwen 32B	Runs slowly	est. 9.4 tok/s7.5–11.3calibrated estimate ±20%	Q4_K_M	22.6 / 44.8 GB	Unified memory	up to 64k	Q2_K (heavy quality loss): Runs well thinking mode
Nanbeige4.3 33B	Runs slowly	est. 9.2 tok/s7.4–11.0calibrated estimate ±20%	Q4_K_M	23.1 / 44.8 GB	Unified memory	up to 64k	Q2_K (heavy quality loss): Runs well thinking mode
Llama 3.3 70B	Runs slowlyLlama 3.3 70B verdict on the Apple M4 Pro	est. 3.0 tok/s2.1–3.9theoretical estimate ±30%	Q4_K_M	45.2 GB RAM	CPU only	up to 32k	—
Qwen3.5 122B-A10B	Won't runTry UD-Q2_K_XL (heavy quality loss): Runs greatQwen3.5 122B-A10B verdict on the Apple M4 Pro	est. 34.1 tok/s27.2–40.9calibrated estimate ±20%	UD-Q2_K_XL	43.6 / 44.8 GB	Unified memory	up to 32k	thinking mode
Solar Open 100B	Won't runTry IQ4_XS: Runs slowly	est. 14.5 tok/s10.1–18.8theoretical estimate ±30%	IQ4_XS	57.1 GB RAM	CPU only	up to 16k	CPU inference — capped at Runs slowly Q2_K (heavy quality loss): Runs well thinking mode
DeepSeek V4 Flash 0731	Won't run	—	MXFP4	needs 155.6 GB	—	—	Needs about 155.6 GB; 60.0 GB of memory is free (44.8 GB usable by the GPU) thinking mode
GLM-5.3 Flash	Won't run	—	Q4_K_M	needs 182.1 GB	—	—	Needs about 182.1 GB; 60.0 GB of memory is free (44.8 GB usable by the GPU) thinking mode
gpt-oss-120b	Won't rungpt-oss-120b verdict on the Apple M4 Pro	—	MXFP4	needs 64.3 GB	—	—	Needs about 64.3 GB; 60.0 GB of memory is free (44.8 GB usable by the GPU) thinking mode
Laguna S 2.1	Won't run	—	Q4_K_M	needs 68.6 GB	—	—	Needs about 68.6 GB; 60.0 GB of memory is free (44.8 GB usable by the GPU) thinking mode
Ling-3.0 Flash	Won't run	—	Q4_K_M	needs 77.7 GB	—	—	Needs about 77.7 GB; 60.0 GB of memory is free (44.8 GB usable by the GPU) thinking mode
Solar Open 2 250B	Won't run	—	IQ4_XS	needs 137.2 GB	—	—	Needs about 137.2 GB; 60.0 GB of memory is free (44.8 GB usable by the GPU) thinking mode

Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.

Verdict by memory size

Q4_K_M verdict for each memory configuration — open the model page for speeds
Model	24 GB	48 GB	64 GB
MiniCPM5 1B	Runs great	Runs great	Runs great
Llama 3.2 1B	Runs great	Runs great	Runs great
Ling-3.0 Tiny	Runs great	Runs great	Runs great
EXAONE 4.0 1.2B	Runs great	Runs great	Runs great
LFM2.5 2.6B	Runs great	Runs great	Runs great
HyperCLOVA X SEED 1.5B	Runs great	Runs great	Runs great
MiniCPM5 2B	Runs great	Runs great	Runs great
Gemma 4 E2B	Runs great	Runs great	Runs great
Mellum2.1 12B-A2.5B Thinking	Runs great	Runs great	Runs great
MiniCPM-V 4.7 35B-A3B	Won't run	Runs great	Runs great
Spark-X2.5 4B	Runs great	Runs great	Runs great
Llama 3.2 3B	Runs great	Runs great	Runs great
gpt-oss-20b	Runs great	Runs great	Runs great
Qwen3.6 35B-A3B	Won't run	Runs great	Runs great
Nemotron 3.5 Lightning 30B-A3B	Won't run	Runs great	Runs great
Qwen3.5 4B	Runs great	Runs great	Runs great
Kanana 1.5 15.7B-A3B	Runs great	Runs great	Runs great
Qwen3.5 35B-A3B	Won't run	Runs great	Runs great
Qwen3 30B-A3B (2507)	Runs slowly	Runs great	Runs great
Gemma 4 E4B	Runs great	Runs great	Runs great
Gemma 4 26B-A4B	Runs slowly	Runs great	Runs great
Qwen3.5 9B	Runs great	Runs great	Runs great
K2-Horizon MoVA 36B-A4B	Won't run	Runs great	Runs great
DeepSeek R1 Distill Llama 8B	Runs great	Runs great	Runs great
Kanana 1.5 8B	Runs great	Runs great	Runs great
Llama 3.1 8B	Runs great	Runs great	Runs great
Nanbeige4.2 3B	Runs great	Runs great	Runs great
DeepSeek R1 0528 Qwen3 8B	Runs great	Runs great	Runs great
Qwen3 8B	Runs great	Runs great	Runs great
K2-Horizon 7B	Runs great	Runs great	Runs great
Gemma 3 12B	Runs great	Runs great	Runs great
Gemma 4 12B	Runs well	Runs well	Runs well
HyperCLOVA X SEED Think 14B	Runs well	Runs well	Runs well
Qwen3 14B	Runs well	Runs well	Runs well
DeepSeek R1 Distill Qwen 14B	Runs well	Runs well	Runs well
Phi-4	Runs well	Runs well	Runs well
Mistral Small 3.2 24B	Runs well	Runs well	Runs well
Gemma 3 27B	Runs slowly	Runs well	Runs well
Kolibri 1	Won't run	Won't run	Runs slowly
Qwen3.6 27B	Runs slowly	Runs slowly	Runs slowly
Muse Glimmer 30B	Runs slowly	Runs slowly	Runs slowly
Qwen3.8 27B	Runs slowly	Runs slowly	Runs slowly
Gemma 4 31B	Runs slowly	Runs slowly	Runs slowly
Granite 4.2 30B	Runs slowly	Runs slowly	Runs slowly
EXAONE 4.0 32B	Runs slowly	Runs slowly	Runs slowly
EXAONE 4.5 33B	Won't run	Runs slowly	Runs slowly
Qwen3.5 27B	Runs slowly	Runs slowly	Runs slowly
Qwen3 32B	Won't run	Runs slowly	Runs slowly
DeepSeek R1 Distill Qwen 32B	Won't run	Runs slowly	Runs slowly
Nanbeige4.3 33B	Won't run	Runs slowly	Runs slowly
Llama 3.3 70B	Won't run	Won't run	Runs slowly
Qwen3.5 122B-A10B	Won't run	Won't run	Won't run
Solar Open 100B	Won't run	Won't run	Won't run
DeepSeek V4 Flash 0731	Won't run	Won't run	Won't run
GLM-5.3 Flash	Won't run	Won't run	Won't run
gpt-oss-120b	Won't run	Won't run	Won't run
Laguna S 2.1	Won't run	Won't run	Won't run
Ling-3.0 Flash	Won't run	Won't run	Won't run
Solar Open 2 250B	Won't run	Won't run	Won't run

Measured results on the Apple M4 Pro

Public benchmarks we calibrate against. Their conditions (context, backend, flags) can differ from the estimates above.

Measured results on the Apple M4 Pro
Model	Quant	Backend	Context	Prompt (tok/s)	Generation (tok/s)	Flags	Source	Measured
llama-2-7b	Q4_0	llama.cpp	512	440.0	50.7	Metal, b1550 (2023)	github.com	2024-11-08
Qwen3.5 27B	Q4_K_M	llama.cpp	512	115.0	9.9	Metal	github.com	2026-07-18
Qwen3.5 9B	Q4_K_M	llama.cpp	4k	—	37.0	—	github.com	2026-07-29

Frequently asked questions

What is the largest model that runs entirely on the Apple M4 Pro?

Kolibri 1 at IQ4_XS (a 43.63 GB file) fits entirely in 64 GB of unified memory with 8k context, at est. 52.1 tok/s (41.7–62.5, calibrated estimate ±20%).

How many local LLMs run well on the Apple M4 Pro?

At Q4_K_M with 8k context, with 64 GB of memory, out of 59 tracked models: 31 run great, 7 run well, 13 run slowly and 8 won't run.

Can the Apple M4 Pro run a 70B model like Llama 3.3 70B?

Runs slowly — CPU only, Q4_K_M: est. 3.0 tok/s (2.1–3.9, theoretical estimate ±30%).

Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.