What are the best models to run on Apple M4 (32GB)?

Based on model rankings and 24 GB usable VRAM: Top Overall: Qwen 3.8 27B (INT4) ~6 tok/s. Top Coding: Qwen3.5-27B (INT4) ~6 tok/s. Optimal Daily Driver: Phi-4 Reasoning Plus (INT4) ~9 tok/s. Maximum Model Size: Falcon-40B (INT4) ~4 tok/s.

How are VRAM, throughput, and latency calculated?

Calculations are determined using apxml.com modeling, combining LLM architecture analysis with GPU hardware physics. VRAM and Context Scaling: Memory requirements are determined from model architecture, including parameter count, layer configuration, and attention structure. The KV cache footprint scales deterministically based on context length, batch size, and cache precision. Throughput (TPS): Token generation is calculated in the memory-bandwidth-bound decode phase, measuring the time required to stream model weights and KV cache relative to hardware memory bandwidth. Latency (TTFT): Time to first token is calculated from the compute operations required during prompt prefill relative to hardware tensor compute capacity.

How accurate are these estimates?

Calculations are calibrated against empirical ground-truth benchmark runs across diverse architectures and hardware. Because the underlying mechanics are benchmark-calibrated, estimates remain accurate across different configurations without needing to run physical tests for every scenario. VRAM Accuracy: Memory estimates are deterministic and closely match actual allocation. Minor differences typically stay within 3% to 5% due to CUDA runtime overhead or memory allocator fragmentation. Speed and Latency Accuracy: Throughput and TTFT typically vary within 5% to 10% depending on the specific inference runtime, kernel implementations, and system power limits.

Best Models to Run on Apple M4 (32GB) (October 2026)

Rank	Model	Parameters	Precision	TPS (Approx.)	TTFT
#33	Qwen 3.8 27B	27B	INT4	6 tok/s	~63.6s
#48	Agnes 3.0 Flash	33B	INT4	5 tok/s	~77.4s
#72	K2 Horizon MoVA 36B A4B	36B (4B active)	INT4	29 tok/s	~13.5s
#83	Qwen3.5-27B	27B	INT4	6 tok/s	~63.6s
#92	Sarvam-30B	32B (2.4B active)	INT4	42 tok/s	~8.7s
#94	Qwen3.6 35B A3B	35B (3B active)	INT4	35 tok/s	~11.0s
#96	Muse Glimmer 30B	30B	INT4	6 tok/s	~70.6s
#100	Phi-4 Reasoning Plus	14B	INT4 Q8	9 tok/s 6 tok/s	~33.5s ~33.5s
#101	MiMo V2 Flash	15B (309B active)	INT4 Q8	1 tok/s 1 tok/s	~696.5s ~758.4s
#108	Gemma 4 26B A4B	25.2B (3.8B active)	INT4	33 tok/s	~11.4s
#109	Gemma 4 12B	11.95B	INT4 Q8	10 tok/s 7 tok/s	~28.7s ~28.7s
#113	Qwen3.5-9B	9B	INT4 Q8 FP16	18 tok/s 11 tok/s 5 tok/s	~21.7s ~21.7s ~23.7s
#114	Qwen3.5-35B-A3B	35B (3B active)	INT4	35 tok/s	~11.0s
#118	K2 Horizon 7B	7B	INT4 Q8 FP16	23 tok/s 13 tok/s 7 tok/s	~16.9s ~17.0s ~17.0s
#128	NVIDIA Nemotron 3 Nano 30B-A3B	3.5B (30B active)	INT4 Q8 FP16	6 tok/s 3 tok/s 2 tok/s	~68.3s ~68.4s ~68.7s
#129	Gemma 4 31B	30.7B	INT4	6 tok/s	~72.2s
#131	Nemotron 3.5 Lightning	30B (3B active)	INT4	12 tok/s	~10.8s
#132	Qwen3.5-4B	4B	INT4 Q8 FP16	37 tok/s 22 tok/s 12 tok/s	~9.9s ~9.9s ~10.0s
#133	Qwen3-30B-A3B	30B (3B active)	INT4	37 tok/s	~9.9s
#136	GPT-OSS 20B	21B (3.6B active)	INT4	14 tok/s	~10.7s
#146	Granite 4.2 8B	8B	INT4 Q8 FP16	20 tok/s 12 tok/s 6 tok/s	~19.3s ~19.3s ~19.4s
#150	Gemma 4 E4B	8B	INT4 Q8 FP16	20 tok/s 12 tok/s 6 tok/s	~19.3s ~19.3s ~19.4s
#151	Nemotron 3.5 Lightning 30B A3B	30B (3B active)	INT4	37 tok/s	~9.9s
#153	Qwen3-32B	32B	INT4	6 tok/s	~75.2s
#156	GLM-4	32B	INT4	4 tok/s	~88.5s
#158	GLM-4V	9B	INT4 Q8 FP16	13 tok/s 9 tok/s 5 tok/s	~21.7s ~21.7s ~23.7s
#159	Gemma 3 27B	27B	INT4	6 tok/s	~63.6s
#160	Phi-4	14B	INT4 Q8	12 tok/s 7 tok/s	~33.5s ~33.5s
#162	DeepSeek-R1 32B	32B	INT4	6 tok/s	~75.2s
#164	Qwen2.5-32B	32B	INT4	6 tok/s	~75.2s
#168	Magistral Small	24B	INT4	5 tok/s	~56.8s
#169	OLMo 3 7B Think	7B	INT4 Q8 FP16	16 tok/s 11 tok/s 6 tok/s	~17.0s ~17.0s ~17.1s
#170	OLMo 3.1 32B Instruct	32B	INT4	4 tok/s	~88.5s
#172	DeepSeek-R1 14B	14B	INT4 Q8	13 tok/s 7 tok/s	~33.5s ~33.5s
#173	Ministral 3 14B	14B	INT4 Q8	9 tok/s 6 tok/s	~33.5s ~33.5s
#177	Gemma 3 12B	12B	INT4 Q8 FP16	14 tok/s 8 tok/s 4 tok/s	~28.8s ~28.8s ~34.0s
#180	OLMo 3 32B Base	32B	INT4	4 tok/s	~88.5s
#181	Mistral-Small-2501	24B	INT4	7 tok/s	~56.7s
#182	Ministral 3 8B	8B	INT4 Q8 FP16	14 tok/s 10 tok/s 5 tok/s	~19.3s ~19.3s ~19.4s
#183	Qwen3.5-2B	2B	INT4 Q8 FP16	64 tok/s 41 tok/s 23 tok/s	~5.3s ~5.3s ~5.3s
#184	MiniCPM5-2B	2B	INT4 Q8 FP16	64 tok/s 41 tok/s 23 tok/s	~5.3s ~5.3s ~5.3s
#185	Qwen2.5-14B	14B	INT4 Q8	12 tok/s 7 tok/s	~33.5s ~33.5s
#186	Gemma 2 27B	27B	INT4	6 tok/s	~63.6s
#187	OLMo 3.1 32B Think	32B	INT4	4 tok/s	~88.5s
#188	Gemma 4 E2B	5.1B	INT4 Q8 FP16	30 tok/s 18 tok/s 9 tok/s	~12.5s ~12.5s ~12.6s
#189	Qwen3-4B	4B	INT4 Q8 FP16	37 tok/s 22 tok/s 12 tok/s	~9.9s ~9.9s ~10.0s
#190	DeepSeek-R1 8B	8B	INT4 Q8 FP16	21 tok/s 12 tok/s 6 tok/s	~19.3s ~19.3s ~19.4s
#193	Ministral 3 3B	3B	INT4 Q8 FP16	29 tok/s 21 tok/s 13 tok/s	~7.6s ~7.6s ~7.6s
#195	Qwen3-14B	14B	INT4 Q8	12 tok/s 7 tok/s	~33.5s ~33.5s
#197	Gemma 2 9B	9B	INT4 Q8 FP16	18 tok/s 11 tok/s 5 tok/s	~21.7s ~21.7s ~23.7s
#198	Qwen2.5-7B	7B	INT4 Q8 FP16	23 tok/s 13 tok/s 7 tok/s	~16.9s ~17.0s ~17.0s
#199	Qwen3-8B	8B	INT4 Q8 FP16	20 tok/s 12 tok/s 6 tok/s	~19.3s ~19.3s ~19.4s
#200	Gemma 3 4B	4B	INT4 Q8 FP16	37 tok/s 22 tok/s 12 tok/s	~9.9s ~9.9s ~10.0s
#201	DeepSeek-R1 7B	7B	INT4 Q8 FP16	24 tok/s 14 tok/s 7 tok/s	~16.9s ~17.0s ~17.0s
#202	Llama 3.1 8B	8B	INT4 Q8 FP16	20 tok/s 12 tok/s 6 tok/s	~19.3s ~19.3s ~19.4s
#204	Qwen3-1.7B	1.7B	INT4 Q8 FP16	72 tok/s 47 tok/s 26 tok/s	~4.5s ~4.5s ~4.5s
#205	Command R	35B	INT4	4 tok/s	~96.5s
#206	Gemma 3 270M	0.27B	INT4 Q8 FP16	161 tok/s 137 tok/s 101 tok/s	~693 ms ~694 ms ~697 ms
#208	Llama 3 8B	8B	INT4 Q8 FP16	20 tok/s 12 tok/s 6 tok/s	~19.3s ~19.3s ~19.4s
#209	Qwen3-0.6B	0.6B	INT4 Q8 FP16	143 tok/s 104 tok/s 64 tok/s	~1.6s ~1.6s ~1.6s
#210	Phi-4-Mini	3.8B	INT4 Q8 FP16	39 tok/s 24 tok/s 13 tok/s	~9.5s ~9.5s ~9.5s
#212	Ministral-8B-2410	8B	INT4 Q8 FP16	20 tok/s 12 tok/s 6 tok/s	~19.3s ~19.3s ~19.4s
#213	DeepSeek-R1 1.5B	1.5B	INT4 Q8 FP16	79 tok/s 52 tok/s 29 tok/s	~4.0s ~4.0s ~4.0s
#214	Llama 3.2 3B	3B	INT4 Q8 FP16	47 tok/s 29 tok/s 16 tok/s	~7.6s ~7.6s ~7.6s
#215	Qwen3.5-0.8B	0.8B	INT4 Q8 FP16	120 tok/s 84 tok/s 51 tok/s	~2.1s ~2.1s ~2.1s
#216	Phi-3-mini	3.8B	INT4 Q8 FP16	39 tok/s 24 tok/s 13 tok/s	~9.5s ~9.5s ~9.5s
#217	Gemma 3n E2B IT	6B (2B active)	INT4 Q8 FP16	29 tok/s 24 tok/s 16 tok/s	~5.6s ~5.6s ~5.7s
#218	Mistral-7B-Instruct-v0.1	7.3B	INT4 Q8 FP16	22 tok/s 13 tok/s 7 tok/s	~17.6s ~17.7s ~17.7s
#219	Llama 3.2 1B	1B	INT4 Q8 FP16	103 tok/s 71 tok/s 42 tok/s	~2.7s ~2.7s ~2.7s
#220	Gemma 2 2B	2B	INT4 Q8 FP16	64 tok/s 41 tok/s 23 tok/s	~5.3s ~5.3s ~5.3s
#221	Phi-3-medium	14B	INT4 Q8	12 tok/s 7 tok/s	~33.5s ~33.5s
#222	OLMo 3 7B Instruct	7B	INT4 Q8 FP16	16 tok/s 11 tok/s 6 tok/s	~17.0s ~17.0s ~17.1s
#223	Yi-34B	34B	INT4	4 tok/s	~93.9s
#224	Qwen2-7B	7B	INT4 Q8 FP16	23 tok/s 13 tok/s 7 tok/s	~16.9s ~17.0s ~17.0s
#225	Phi-3-small	7B	INT4 Q8 FP16	23 tok/s 13 tok/s 7 tok/s	~16.9s ~17.0s ~17.0s
#226	Gemma 3 1B	1B	INT4 Q8 FP16	103 tok/s 71 tok/s 42 tok/s	~2.7s ~2.7s ~2.7s
#227	Mistral-7B-Instruct-v0.2	7.3B	INT4 Q8 FP16	22 tok/s 13 tok/s 7 tok/s	~17.6s ~17.7s ~17.7s
#229	Gemma 1 7B	7B	INT4 Q8 FP16	16 tok/s 11 tok/s 6 tok/s	~17.0s ~17.0s ~17.1s
#230	Gemma 1 2B	2B	INT4 Q8 FP16	70 tok/s 43 tok/s 23 tok/s	~5.3s ~5.3s ~5.3s
#231	ChatGLM3-6B	6B	INT4 Q8 FP16	18 tok/s 12 tok/s 7 tok/s	~14.6s ~14.6s ~14.7s
#232	ChatGLM2-6B	6B	INT4 Q8 FP16	18 tok/s 12 tok/s 7 tok/s	~14.6s ~14.6s ~14.7s
#233	ChatGLM-6B	6B	INT4 Q8 FP16	18 tok/s 12 tok/s 7 tok/s	~14.6s ~14.6s ~14.7s
Unranked Models (Sorted by Speed)
-	Qwen2-0.5B	0.5B	INT4 Q8 FP16	157 tok/s 117 tok/s 74 tok/s	~1.3s ~1.3s ~1.3s
-	Qwen2.5-0.5B	0.5B	INT4 Q8 FP16	157 tok/s 117 tok/s 74 tok/s	~1.3s ~1.3s ~1.3s
-	ERNIE-4.5-0.3B	0.3B	INT4 Q8 FP16	152 tok/s 128 tok/s 93 tok/s	~773 ms ~775 ms ~778 ms
-	ERNIE-4.5-0.3B-Base	0.3B	INT4 Q8 FP16	152 tok/s 128 tok/s 93 tok/s	~773 ms ~775 ms ~778 ms
-	Falcon-1B	1B	INT4 Q8 FP16	113 tok/s 75 tok/s 43 tok/s	~2.7s ~2.7s ~2.7s
-	Falcon3-1B	1B	INT4 Q8 FP16	103 tok/s 71 tok/s 42 tok/s	~2.7s ~2.7s ~2.7s
-	Qwen2-1.5B	1.5B	INT4 Q8 FP16	79 tok/s 52 tok/s 29 tok/s	~4.0s ~4.0s ~4.0s
-	Qwen2.5-1.5B	1.5B	INT4 Q8 FP16	79 tok/s 52 tok/s 29 tok/s	~4.0s ~4.0s ~4.0s
-	Spark X2.5 1.7B	1.7B	INT4 Q8 FP16	72 tok/s 47 tok/s 26 tok/s	~4.5s ~4.5s ~4.5s
-	Hy-MT2 1.8B	1.8B	INT4 Q8 FP16	69 tok/s 45 tok/s 25 tok/s	~4.7s ~4.7s ~4.8s
-	Falcon-3B	3B	INT4 Q8 FP16	51 tok/s 30 tok/s 16 tok/s	~7.6s ~7.6s ~7.6s
-	CroissantLLM Base	1.3B	INT4 Q8 FP16	49 tok/s 40 tok/s 26 tok/s	~3.5s ~3.5s ~3.5s
-	Phi-1	1.3B	INT4 Q8 FP16	49 tok/s 40 tok/s 26 tok/s	~3.5s ~3.5s ~3.5s
-	Phi-1.5	1.3B	INT4 Q8 FP16	49 tok/s 40 tok/s 26 tok/s	~3.5s ~3.5s ~3.5s
-	DeepSeek-R1 3B	3B	INT4 Q8 FP16	48 tok/s 29 tok/s 16 tok/s	~7.6s ~7.6s ~7.6s
-	Falcon3-3B	3B	INT4 Q8 FP16	47 tok/s 29 tok/s 16 tok/s	~7.6s ~7.6s ~7.6s
-	Qwen2.5-3B	3B	INT4 Q8 FP16	47 tok/s 29 tok/s 16 tok/s	~7.6s ~7.6s ~7.6s
-	ERNIE-4.5-21B-A3B	21B (3B active)	INT4 Q8	40 tok/s 25 tok/s	~9.3s ~10.1s
-	ERNIE-4.5-21B-A3B-Base	21B (3B active)	INT4 Q8	40 tok/s 25 tok/s	~9.3s ~10.1s
-	ERNIE-4.5-VL-28B-A3B	28B (3B active)	INT4	38 tok/s	~9.8s
-	ERNIE-4.5-VL-28B-A3B-Base	28B (3B active)	INT4	38 tok/s	~9.8s
-	Hy-MT2 30B A3B	30B (3B active)	INT4	37 tok/s	~9.9s
-	Spark X2.5 4B	4B	INT4 Q8 FP16	37 tok/s 22 tok/s 12 tok/s	~9.9s ~9.9s ~10.0s
-	Phi-2	2.7B	INT4 Q8 FP16	30 tok/s 23 tok/s 14 tok/s	~6.9s ~6.9s ~6.9s
-	MaLLaM-3B	3B	INT4 Q8 FP16	29 tok/s 21 tok/s 13 tok/s	~7.6s ~7.6s ~7.6s
-	SmolLM3 3B	3B	INT4 Q8 FP16	29 tok/s 21 tok/s 13 tok/s	~7.6s ~7.6s ~7.6s
-	Falcon-7B	7B	INT4 Q8 FP16	24 tok/s 14 tok/s 7 tok/s	~16.9s ~17.0s ~17.0s
-	Falcon3-7B	7B	INT4 Q8 FP16	23 tok/s 13 tok/s 7 tok/s	~16.9s ~17.0s ~17.0s
-	Hy-MT2 7B	7B	INT4 Q8 FP16	23 tok/s 13 tok/s 7 tok/s	~16.9s ~17.0s ~17.0s
-	Mistral-7B-v0.1	7.3B	INT4 Q8 FP16	22 tok/s 13 tok/s 7 tok/s	~17.6s ~17.7s ~17.7s
-	ChatGLM3-6B-32K	6B	INT4 Q8 FP16	18 tok/s 12 tok/s 7 tok/s	~14.6s ~14.6s ~14.7s
-	LensVLM 9B	9B	INT4 Q8 FP16	18 tok/s 11 tok/s 5 tok/s	~21.7s ~21.7s ~23.7s
-	MiMo V2.6 Distill Qwen 9B	9B	INT4 Q8 FP16	18 tok/s 11 tok/s 5 tok/s	~21.7s ~21.7s ~23.7s
-	Yi-6B	6B	INT4 Q8 FP16	18 tok/s 12 tok/s 7 tok/s	~14.6s ~14.6s ~14.7s
-	Falcon3-10B	10B	INT4 Q8 FP16	17 tok/s 10 tok/s 5 tok/s	~24.0s ~24.1s ~26.2s
-	Kimi-VL-A3B-Instruct	16B (3B active)	INT4 Q8	17 tok/s 14 tok/s	~8.9s ~9.7s
-	Falcon2-11B	11B	INT4 Q8 FP16	16 tok/s 9 tok/s 4 tok/s	~26.4s ~26.4s ~28.8s
-	Hunyuan Lite	7B	INT4 Q8 FP16	16 tok/s 11 tok/s 6 tok/s	~17.0s ~17.0s ~17.1s
-	OLMo 3 7B Base	7B	INT4 Q8 FP16	16 tok/s 11 tok/s 6 tok/s	~17.0s ~17.0s ~17.1s
-	SEA-LION-7B	7.1B	INT4 Q8 FP16	16 tok/s 11 tok/s 6 tok/s	~17.2s ~17.2s ~17.3s
-	SEA-LION-7B-Instruct	7.1B	INT4 Q8 FP16	16 tok/s 11 tok/s 6 tok/s	~17.2s ~17.2s ~17.3s
-	Sahabat-AI-Llama3-8B-Instruct	8B	INT4 Q8 FP16	14 tok/s 10 tok/s 5 tok/s	~19.3s ~19.3s ~19.4s
-	Typhoon-2-8B	8B	INT4 Q8 FP16	14 tok/s 10 tok/s 5 tok/s	~19.3s ~19.3s ~19.4s
-	GLM-4-9B	9B	INT4 Q8 FP16	13 tok/s 9 tok/s 5 tok/s	~21.7s ~21.7s ~23.7s
-	GLM-4-9B-Chat	9B	INT4 Q8 FP16	13 tok/s 9 tok/s 5 tok/s	~21.7s ~21.7s ~23.7s
-	GLM-4-9B-Chat-1M	9B	INT4 Q8 FP16	13 tok/s 9 tok/s 5 tok/s	~21.7s ~21.7s ~23.7s
-	Sahabat-AI-Gemma2-9B	9.2B	INT4 Q8 FP16	13 tok/s 8 tok/s 5 tok/s	~22.1s ~22.2s ~24.2s
-	Sahabat-AI-Gemma2-9B-Instruct	9.2B	INT4 Q8 FP16	13 tok/s 8 tok/s 5 tok/s	~22.1s ~22.2s ~24.2s
-	Yi-9B	9B	INT4 Q8 FP16	13 tok/s 9 tok/s 5 tok/s	~21.7s ~21.7s ~23.7s
-	GreenMind-14B-R1	14B	INT4 Q8	9 tok/s 6 tok/s	~33.5s ~33.5s
-	Falcon-40B	40B	INT4	4 tok/s	~101.6s

Apple M4 (32GB)

VRAM Scaling by Context Length

Best Models to Run on Apple M4 (32GB)

Inference Capacity

Fine-Tuning Capacity

Workload Recommendations

Frequently Asked Questions