Apple M3 Max (64GB)
The Apple M3 Max (64GB) uses a unified memory architecture. For reliable local LLM inference without OS memory pressure, this benchmark models a 75% usable allocation (48 GB) with 400 GB/s unified memory bandwidth.
Memory
64 GB
Usable Memory Ceiling
48 GB (75% usable budget)
Bandwidth
400 GB/s
Max Inference Class
32B Models (Q4)
TDP
115W
VRAM Scaling by Context Length
Estimated memory requirements as context length increases. Curves crossing above the reference line indicate Out of Memory (OOM).
Precision:
Best Models to Run on Apple M3 Max (64GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on Apple M3 Max (64GB).
Sort by:
Context:
KV Cache:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#36 | Qwen 3.8 27B | 27B | INT4 Q8 | 21 tok/s 12 tok/s | ~16.5s ~16.6s | |
#80 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 Q8 | 82 tok/s 58 tok/s | ~3.2s ~3.2s | |
#86 | Qwen3.5-27B | 27B | INT4 Q8 | 21 tok/s 12 tok/s | ~16.5s ~16.6s | |
#93 | Sarvam-30B | 32B (2.4B active) | INT4 Q8 | 106 tok/s 80 tok/s | ~2.3s ~2.3s | |
#99 | Muse Glimmer 30B | 30B | INT4 Q8 | 19 tok/s 11 tok/s | ~18.3s ~18.4s | |
#102 | Phi-4 Reasoning Plus | 14B | INT4 Q8 FP16 | 27 tok/s 18 tok/s 10 tok/s | ~8.7s ~8.7s ~8.8s | |
#103 | Qwen3.6 35B A3B | 35B (3B active) | INT4 Q8 | 95 tok/s 70 tok/s | ~2.6s ~2.6s | |
#105 | MiMo V2 Flash | 15B (309B active) | INT4 Q8 FP16 | 2 tok/s 1 tok/s 1 tok/s | ~180.7s ~181.1s ~182.0s | |
#110 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 Q8 | 88 tok/s 61 tok/s | ~3.0s ~3.0s | |
#117 | Nemotron 3.5 Bolt 74B A9B | 74B | INT4 | 8 tok/s | ~48.7s | |
#120 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 Q8 | 95 tok/s 70 tok/s | ~2.6s ~2.6s | |
#121 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 53 tok/s 33 tok/s 17 tok/s | ~5.6s ~5.6s ~5.7s | |
#127 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 65 tok/s 41 tok/s 22 tok/s | ~4.4s ~4.4s ~4.4s | |
#130 | Gemma 4 12B | 11.95B | INT4 Q8 FP16 | 31 tok/s 21 tok/s 12 tok/s | ~7.4s ~7.5s ~7.5s | |
#136 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 97 tok/s 64 tok/s 36 tok/s | ~2.6s ~2.6s ~2.6s | |
#139 | GPT-OSS 20B | 21B (3.6B active) | INT4 Q8 FP16 | 43 tok/s 37 tok/s 24 tok/s | ~2.8s ~2.8s ~3.3s | |
#140 | GLM-4V | 9B | INT4 Q8 FP16 | 39 tok/s 27 tok/s 16 tok/s | ~5.6s ~5.6s ~5.7s | |
#145 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 18 tok/s 10 tok/s 5 tok/s | ~17.7s ~17.8s ~17.9s | |
#150 | Qwen3-30B-A3B | 30B (3B active) | INT4 Q8 | 97 tok/s 70 tok/s | ~2.6s ~2.6s | |
#152 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 59 tok/s 36 tok/s 20 tok/s | ~5.0s ~5.0s ~5.0s | |
#157 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 59 tok/s 36 tok/s 20 tok/s | ~5.0s ~5.0s ~5.0s | |
#158 | Mistral Large 3 | 41B (675B active) | INT4 | 1 tok/s | ~394.4s | |
#159 | Qwen2.5-72B | 72B | INT4 | 8 tok/s | ~47.4s | |
#161 | GLM-4 | 32B | INT4 Q8 | 14 tok/s 8 tok/s | ~19.5s ~21.3s | |
#162 | DeepSeek-R1 70B | 70B | INT4 | 9 tok/s | ~42.4s | |
#163 | Gemma 3 27B | 27B | INT4 Q8 | 21 tok/s 12 tok/s | ~16.5s ~16.6s | |
#164 | Phi-4 | 14B | INT4 Q8 FP16 | 37 tok/s 22 tok/s 12 tok/s | ~8.7s ~8.7s ~8.7s | |
#165 | Llama 3.3 70B | 70B | INT4 | 8 tok/s | ~42.4s | |
#166 | Qwen3-32B | 32B | INT4 Q8 | 18 tok/s 10 tok/s | ~19.5s ~19.6s | |
#167 | Hunyuan Standard | 52B (389B active) | INT4 | 2 tok/s | ~227.9s | |
#168 | DeepSeek-R1 32B | 32B | INT4 Q8 | 18 tok/s 10 tok/s | ~19.5s ~19.5s | |
#169 | Gemma 4 31B | 30.7B | INT4 Q8 | 18 tok/s 10 tok/s | ~18.7s ~18.8s | |
#171 | Magistral Small | 24B | INT4 Q8 | 17 tok/s 11 tok/s | ~14.7s ~14.8s | |
#172 | Qwen2.5-32B | 32B | INT4 Q8 | 18 tok/s 10 tok/s | ~19.5s ~19.6s | |
#174 | OLMo 3.1 32B Instruct | 32B | INT4 Q8 | 14 tok/s 8 tok/s | ~19.5s ~21.3s | |
#175 | Llama 3.1 70B | 70B | INT4 | 8 tok/s | ~42.4s | |
#176 | DeepSeek-R1 14B | 14B | INT4 Q8 FP16 | 38 tok/s 22 tok/s 12 tok/s | ~8.7s ~8.7s ~8.7s | |
#177 | Ministral 3 14B | 14B | INT4 Q8 FP16 | 27 tok/s 18 tok/s 10 tok/s | ~8.7s ~8.7s ~8.8s | |
#180 | Gemma 3 12B | 12B | INT4 Q8 FP16 | 42 tok/s 25 tok/s 13 tok/s | ~7.5s ~7.5s ~7.5s | |
#183 | Qwen2-72B | 72B | INT4 | 8 tok/s | ~47.4s | |
#184 | Mistral-Small-2501 | 24B | INT4 Q8 FP16 | 23 tok/s 13 tok/s 6 tok/s | ~14.7s ~14.8s ~17.4s | |
#185 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 43 tok/s 30 tok/s 17 tok/s | ~5.0s ~5.0s ~5.0s | |
#186 | Gemma 2 27B | 27B | INT4 Q8 | 21 tok/s 12 tok/s | ~16.5s ~16.6s | |
#187 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 47 tok/s 33 tok/s 20 tok/s | ~4.4s ~4.4s ~4.4s | |
#188 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 142 tok/s 103 tok/s 64 tok/s | ~1.4s ~1.4s ~1.4s | |
#189 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 142 tok/s 103 tok/s 64 tok/s | ~1.4s ~1.4s ~1.4s | |
#190 | Qwen2.5-14B | 14B | INT4 Q8 FP16 | 37 tok/s 22 tok/s 12 tok/s | ~8.7s ~8.7s ~8.7s | |
#191 | OLMo 3.1 32B Think | 32B | INT4 Q8 | 14 tok/s 8 tok/s | ~19.5s ~21.3s | |
#192 | Llama 3 70B | 70B | INT4 | 8 tok/s | ~42.4s | |
#193 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 82 tok/s 53 tok/s 29 tok/s | ~3.2s ~3.3s ~3.3s | |
#195 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 78 tok/s 61 tok/s 40 tok/s | ~2.0s ~2.0s ~2.0s | |
#196 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 60 tok/s 37 tok/s 20 tok/s | ~5.0s ~5.0s ~5.0s | |
#198 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 53 tok/s 33 tok/s 17 tok/s | ~5.6s ~5.6s ~5.7s | |
#199 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 Q8 | 97 tok/s 70 tok/s | ~2.6s ~2.6s | |
#200 | Kimi Linear 48B A3B Instruct | 48B (3B active) | INT4 | 33 tok/s | ~2.8s | |
#201 | Qwen3-4B | 4B | INT4 Q8 FP16 | 97 tok/s 64 tok/s 36 tok/s | ~2.6s ~2.6s ~2.6s | |
#202 | Qwen3-14B | 14B | INT4 Q8 FP16 | 37 tok/s 22 tok/s 12 tok/s | ~8.7s ~8.7s ~8.7s | |
#203 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 97 tok/s 64 tok/s 36 tok/s | ~2.6s ~2.6s ~2.6s | |
#204 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 67 tok/s 41 tok/s 22 tok/s | ~4.4s ~4.4s ~4.4s | |
#205 | OLMo 3 32B Base | 32B | INT4 Q8 | 14 tok/s 8 tok/s | ~19.5s ~21.3s | |
#206 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 208 tok/s 171 tok/s 122 tok/s | ~558 ms ~559 ms ~561 ms | |
#207 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 59 tok/s 36 tok/s 20 tok/s | ~5.0s ~5.0s ~5.0s | |
#207 | Qwen3-8B | 8B | INT4 Q8 FP16 | 59 tok/s 36 tok/s 20 tok/s | ~5.0s ~5.0s ~5.0s | |
#210 | Nemotron 3.5 Lightning | 30B (3B active) | INT4 Q8 | 38 tok/s 35 tok/s | ~2.6s ~2.6s | |
#211 | Command R | 35B | INT4 Q8 | 13 tok/s 8 tok/s | ~21.3s ~23.2s | |
#212 | Llama 3 8B | 8B | INT4 Q8 FP16 | 59 tok/s 36 tok/s 20 tok/s | ~5.0s ~5.0s ~5.0s | |
#213 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 154 tok/s 114 tok/s 73 tok/s | ~1.2s ~1.2s ~1.2s | |
#214 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 240 tok/s 222 tok/s 189 tok/s | ~186 ms ~186 ms ~187 ms | |
#216 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 227 tok/s 192 tok/s 144 tok/s | ~413 ms ~414 ms ~415 ms | |
#217 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 100 tok/s 66 tok/s 38 tok/s | ~2.5s ~2.5s ~2.5s | |
#218 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 65 tok/s 41 tok/s 22 tok/s | ~4.4s ~4.4s ~4.4s | |
#219 | Mixtral-8x7B-v0.1 | 46.7B (7B active) | INT4 Q8 | 58 tok/s 34 tok/s | ~5.1s ~6.0s | |
#220 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 59 tok/s 36 tok/s 20 tok/s | ~5.0s ~5.0s ~5.0s | |
#221 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 163 tok/s 123 tok/s 80 tok/s | ~1.0s ~1.0s ~1.0s | |
#222 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 115 tok/s 79 tok/s 47 tok/s | ~2.0s ~2.0s ~2.0s | |
#223 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 100 tok/s 66 tok/s 38 tok/s | ~2.5s ~2.5s ~2.5s | |
#224 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 78 tok/s 67 tok/s 48 tok/s | ~1.5s ~1.5s ~1.5s | |
#225 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 142 tok/s 103 tok/s 64 tok/s | ~1.4s ~1.4s ~1.4s | |
#226 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 63 tok/s 39 tok/s 21 tok/s | ~4.6s ~4.6s ~4.6s | |
#227 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 192 tok/s 153 tok/s 106 tok/s | ~708 ms ~710 ms ~713 ms | |
#228 | Phi-3-medium | 14B | INT4 Q8 FP16 | 37 tok/s 22 tok/s 12 tok/s | ~8.7s ~8.7s ~8.7s | |
#229 | Yi-34B | 34B | INT4 Q8 | 13 tok/s 8 tok/s | ~20.7s ~22.6s | |
#230 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 47 tok/s 33 tok/s 20 tok/s | ~4.4s ~4.4s ~4.4s | |
#231 | Qwen2-7B | 7B | INT4 Q8 FP16 | 65 tok/s 41 tok/s 22 tok/s | ~4.4s ~4.4s ~4.4s | |
#232 | Phi-3-small | 7B | INT4 Q8 FP16 | 65 tok/s 41 tok/s 22 tok/s | ~4.4s ~4.4s ~4.4s | |
#233 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 63 tok/s 39 tok/s 21 tok/s | ~4.6s ~4.6s ~4.6s | |
#234 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 192 tok/s 153 tok/s 106 tok/s | ~708 ms ~710 ms ~713 ms | |
#236 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 47 tok/s 33 tok/s 20 tok/s | ~4.4s ~4.4s ~4.4s | |
#237 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 151 tok/s 108 tok/s 66 tok/s | ~1.4s ~1.4s ~1.4s | |
#238 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 52 tok/s 37 tok/s 23 tok/s | ~3.8s ~3.8s ~3.8s | |
#239 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 52 tok/s 37 tok/s 23 tok/s | ~3.8s ~3.8s ~3.8s | |
#240 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 52 tok/s 37 tok/s 23 tok/s | ~3.8s ~3.8s ~3.8s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 260 tok/s 236 tok/s 195 tok/s | ~206 ms ~207 ms ~208 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 237 tok/s 205 tok/s 158 tok/s | ~342 ms ~343 ms ~345 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 237 tok/s 205 tok/s 158 tok/s | ~342 ms ~343 ms ~345 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 233 tok/s 215 tok/s 181 tok/s | ~207 ms ~207 ms ~208 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 233 tok/s 215 tok/s 181 tok/s | ~207 ms ~207 ms ~208 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 227 tok/s 192 tok/s 144 tok/s | ~413 ms ~414 ms ~415 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 201 tok/s 158 tok/s 108 tok/s | ~708 ms ~710 ms ~713 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 192 tok/s 153 tok/s 106 tok/s | ~708 ms ~710 ms ~713 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 192 tok/s 153 tok/s 106 tok/s | ~708 ms ~710 ms ~713 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 163 tok/s 123 tok/s 80 tok/s | ~1.0s ~1.0s ~1.0s | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 163 tok/s 123 tok/s 80 tok/s | ~1.0s ~1.0s ~1.0s | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 154 tok/s 114 tok/s 73 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 150 tok/s 111 tok/s 70 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 121 tok/s 82 tok/s 47 tok/s | ~2.0s ~2.0s ~2.0s | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 119 tok/s 101 tok/s 73 tok/s | ~905 ms ~907 ms ~911 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 119 tok/s 101 tok/s 73 tok/s | ~905 ms ~907 ms ~911 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 119 tok/s 101 tok/s 73 tok/s | ~905 ms ~907 ms ~911 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 117 tok/s 80 tok/s 47 tok/s | ~2.0s ~2.0s ~2.0s | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 FP16 | 117 tok/s 85 tok/s 52 tok/s | ~1.9s ~1.9s ~1.9s | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 115 tok/s 79 tok/s 47 tok/s | ~2.0s ~2.0s ~2.0s | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 115 tok/s 79 tok/s 47 tok/s | ~2.0s ~2.0s ~2.0s | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 115 tok/s 79 tok/s 47 tok/s | ~2.0s ~2.0s ~2.0s | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 115 tok/s 79 tok/s 47 tok/s | ~2.0s ~2.0s ~2.0s | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 115 tok/s 79 tok/s 47 tok/s | ~2.0s ~2.0s ~2.0s | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 115 tok/s 79 tok/s 47 tok/s | ~2.0s ~2.0s ~2.0s | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 Q8 FP16 | 108 tok/s 80 tok/s 45 tok/s | ~2.2s ~2.2s ~2.6s | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 Q8 FP16 | 101 tok/s 73 tok/s 42 tok/s | ~2.4s ~2.4s ~2.6s | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 Q8 FP16 | 101 tok/s 73 tok/s 42 tok/s | ~2.4s ~2.4s ~2.6s | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 Q8 | 98 tok/s 71 tok/s | ~2.5s ~2.5s | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 Q8 | 98 tok/s 71 tok/s | ~2.5s ~2.5s | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 97 tok/s 64 tok/s 36 tok/s | ~2.6s ~2.6s ~2.6s | |
- | Hy-Memory 30B A3B | 30B (3B active) | INT4 Q8 | 97 tok/s 70 tok/s | ~2.6s ~2.6s | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 Q8 | 97 tok/s 70 tok/s | ~2.6s ~2.6s | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 97 tok/s 64 tok/s 36 tok/s | ~2.6s ~2.6s ~2.6s | |
- | MiniCPM-V 4.7 35B A3B | 35B (3B active) | INT4 Q8 | 95 tok/s 70 tok/s | ~2.6s ~2.6s | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 93 tok/s 76 tok/s 53 tok/s | ~1.4s ~1.4s ~1.4s | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 82 tok/s 65 tok/s 43 tok/s | ~1.8s ~1.8s ~1.8s | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 78 tok/s 61 tok/s 40 tok/s | ~2.0s ~2.0s ~2.0s | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 78 tok/s 61 tok/s 40 tok/s | ~2.0s ~2.0s ~2.0s | |
- | AliceAI Foundation 80B A3B Base | 80B (3B active) | INT4 | 73 tok/s | ~3.8s | |
- | Kolibri 1 | 78B (3.5B active) | INT4 | 69 tok/s | ~4.1s | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 68 tok/s 42 tok/s 22 tok/s | ~4.4s ~4.4s ~4.4s | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 65 tok/s 41 tok/s 22 tok/s | ~4.4s ~4.4s ~4.4s | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 65 tok/s 41 tok/s 22 tok/s | ~4.4s ~4.4s ~4.4s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 63 tok/s 39 tok/s 21 tok/s | ~4.6s ~4.6s ~4.6s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 FP16 | 60 tok/s 37 tok/s 20 tok/s | ~5.0s ~5.0s ~5.0s | |
- | LensVLM 9B | 9B | INT4 Q8 FP16 | 53 tok/s 33 tok/s 17 tok/s | ~5.6s ~5.6s ~5.7s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 FP16 | 53 tok/s 33 tok/s 17 tok/s | ~5.6s ~5.6s ~5.7s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 52 tok/s 37 tok/s 23 tok/s | ~3.8s ~3.8s ~3.8s | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 52 tok/s 37 tok/s 23 tok/s | ~3.8s ~3.8s ~3.8s | |
- | Falcon3-10B | 10B | INT4 Q8 FP16 | 49 tok/s 30 tok/s 16 tok/s | ~6.2s ~6.2s ~6.3s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 Q8 FP16 | 49 tok/s 43 tok/s 31 tok/s | ~2.3s ~2.3s ~2.3s | |
- | Falcon2-11B | 11B | INT4 Q8 FP16 | 47 tok/s 28 tok/s 15 tok/s | ~6.8s ~6.9s ~6.9s | |
- | Hunyuan Lite | 7B | INT4 Q8 FP16 | 47 tok/s 33 tok/s 20 tok/s | ~4.4s ~4.4s ~4.4s | |
- | OLMo 3 7B Base | 7B | INT4 Q8 FP16 | 47 tok/s 33 tok/s 20 tok/s | ~4.4s ~4.4s ~4.4s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 FP16 | 46 tok/s 33 tok/s 19 tok/s | ~4.5s ~4.5s ~4.5s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 FP16 | 46 tok/s 33 tok/s 19 tok/s | ~4.5s ~4.5s ~4.5s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 FP16 | 43 tok/s 30 tok/s 17 tok/s | ~5.0s ~5.0s ~5.0s | |
- | Typhoon-2-8B | 8B | INT4 Q8 FP16 | 43 tok/s 30 tok/s 17 tok/s | ~5.0s ~5.0s ~5.0s | |
- | GLM-4-9B | 9B | INT4 Q8 FP16 | 39 tok/s 27 tok/s 16 tok/s | ~5.6s ~5.6s ~5.7s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 FP16 | 39 tok/s 27 tok/s 16 tok/s | ~5.6s ~5.6s ~5.7s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 FP16 | 39 tok/s 27 tok/s 16 tok/s | ~5.6s ~5.6s ~5.7s | |
- | Yi-9B | 9B | INT4 Q8 FP16 | 39 tok/s 27 tok/s 16 tok/s | ~5.6s ~5.6s ~5.7s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 FP16 | 38 tok/s 26 tok/s 15 tok/s | ~5.8s ~5.8s ~5.8s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 FP16 | 38 tok/s 26 tok/s 15 tok/s | ~5.8s ~5.8s ~5.8s | |
- | GreenMind-14B-R1 | 14B | INT4 Q8 FP16 | 27 tok/s 18 tok/s 10 tok/s | ~8.7s ~8.7s ~8.8s | |
- | AREX-2 | 27B | INT4 Q8 | 21 tok/s 12 tok/s | ~16.5s ~16.6s | |
- | PPLX Decider v1 27B | 27B | INT4 Q8 | 21 tok/s 12 tok/s | ~16.5s ~16.6s | |
- | PPLX Decider v1.1 27B | 27B | INT4 Q8 | 21 tok/s 12 tok/s | ~16.5s ~16.6s | |
- | Agnes 3.0 Flash | 33B | INT4 Q8 | 17 tok/s 10 tok/s | ~20.1s ~20.1s | |
- | Falcon-40B | 40B | INT4 Q8 | 15 tok/s 8 tok/s | ~24.3s ~26.4s | |
- | Kimi-Dev-72B | 72B | INT4 | 6 tok/s | ~51.3s | |
- | Typhoon-2-70B | 70B | INT4 | 6 tok/s | ~49.9s | |
Inference Capacity
Maximum model parameter class runnable by weight precision.
Context:
4-bit
32B Models
8-bit
32B Models
16-bit
14B Models
Fine-Tuning Capacity
Hardware capacity for local training and adapter fine-tuning.
Context Length:
QLoRA
32B Models
LoRA
14B Models
Full Parameter Training
7B-8B Models
Workload Recommendations
Guidance for optimal precision and operational ceilings on Apple M3 Max (64GB).
Inference Sweet Spot
Optimized for 14B models at uncompressed or Q8 precision, and 32B models at Q4 with up to 32k context.
Bandwidth & Speed Profile
With 400 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 89 tok/s on an 8B Q4 model and 11 tok/s on a 70B Q4 model.
Unified Memory Budget
Modeled with a 75% usable allocation budget to preserve system RAM for macOS and display compositor processes.
Frequently Asked Questions
©2025 ApX Machine Learning