Apple M5 Max (64GB)
The Apple M5 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 614 GB/s unified memory bandwidth.
Memory
64 GB
Usable Memory Ceiling
48 GB (75% usable budget)
Bandwidth
614 GB/s
Max Inference Class
32B Models (Q4)
TDP
150W
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 M5 Max (64GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on Apple M5 Max (64GB).
Sort by:
Context:
KV Cache:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#36 | Qwen 3.8 27B | 27B | INT4 Q8 | 30 tok/s 18 tok/s | ~16.3s ~16.3s | |
#80 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 Q8 | 110 tok/s 80 tok/s | ~3.2s ~3.2s | |
#86 | Qwen3.5-27B | 27B | INT4 Q8 | 30 tok/s 18 tok/s | ~16.3s ~16.3s | |
#93 | Sarvam-30B | 32B (2.4B active) | INT4 Q8 | 137 tok/s 108 tok/s | ~2.2s ~2.2s | |
#99 | Muse Glimmer 30B | 30B | INT4 Q8 | 28 tok/s 16 tok/s | ~18.1s ~18.1s | |
#102 | Phi-4 Reasoning Plus | 14B | INT4 Q8 FP16 | 40 tok/s 27 tok/s 16 tok/s | ~8.6s ~8.6s ~8.6s | |
#103 | Qwen3.6 35B A3B | 35B (3B active) | INT4 Q8 | 125 tok/s 95 tok/s | ~2.6s ~2.6s | |
#105 | MiMo V2 Flash | 15B (309B active) | INT4 Q8 FP16 | 3 tok/s 2 tok/s 1 tok/s | ~178.3s ~178.6s ~179.2s | |
#110 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 Q8 | 117 tok/s 85 tok/s | ~2.9s ~2.9s | |
#117 | Nemotron 3.5 Bolt 74B A9B | 74B | INT4 | 11 tok/s | ~48.0s | |
#120 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 Q8 | 125 tok/s 95 tok/s | ~2.6s ~2.6s | |
#121 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 75 tok/s 47 tok/s 26 tok/s | ~5.6s ~5.6s ~5.6s | |
#127 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 90 tok/s 58 tok/s 33 tok/s | ~4.3s ~4.4s ~4.4s | |
#130 | Gemma 4 12B | 11.95B | INT4 Q8 FP16 | 45 tok/s 31 tok/s 18 tok/s | ~7.3s ~7.4s ~7.4s | |
#136 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 127 tok/s 88 tok/s 53 tok/s | ~2.5s ~2.5s ~2.6s | |
#139 | GPT-OSS 20B | 21B (3.6B active) | INT4 Q8 FP16 | 61 tok/s 53 tok/s 35 tok/s | ~2.7s ~2.7s ~3.2s | |
#140 | GLM-4V | 9B | INT4 Q8 FP16 | 56 tok/s 39 tok/s 23 tok/s | ~5.6s ~5.6s ~5.6s | |
#145 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 26 tok/s 16 tok/s 8 tok/s | ~17.5s ~17.5s ~17.6s | |
#150 | Qwen3-30B-A3B | 30B (3B active) | INT4 Q8 | 127 tok/s 96 tok/s | ~2.5s ~2.5s | |
#152 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 82 tok/s 52 tok/s 29 tok/s | ~4.9s ~5.0s ~5.0s | |
#157 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 82 tok/s 52 tok/s 29 tok/s | ~4.9s ~5.0s ~5.0s | |
#158 | Mistral Large 3 | 41B (675B active) | INT4 | 1 tok/s | ~389.3s | |
#159 | Qwen2.5-72B | 72B | INT4 | 12 tok/s | ~46.8s | |
#161 | GLM-4 | 32B | INT4 Q8 | 21 tok/s 13 tok/s | ~19.3s ~21.0s | |
#162 | DeepSeek-R1 70B | 70B | INT4 | 13 tok/s | ~41.8s | |
#163 | Gemma 3 27B | 27B | INT4 Q8 | 30 tok/s 18 tok/s | ~16.3s ~16.3s | |
#164 | Phi-4 | 14B | INT4 Q8 FP16 | 53 tok/s 32 tok/s 17 tok/s | ~8.6s ~8.6s ~8.6s | |
#165 | Llama 3.3 70B | 70B | INT4 | 13 tok/s | ~41.8s | |
#166 | Qwen3-32B | 32B | INT4 Q8 | 26 tok/s 15 tok/s | ~19.3s ~19.3s | |
#167 | Hunyuan Standard | 52B (389B active) | INT4 | 2 tok/s | ~224.9s | |
#168 | DeepSeek-R1 32B | 32B | INT4 Q8 | 27 tok/s 15 tok/s | ~19.3s ~19.3s | |
#169 | Gemma 4 31B | 30.7B | INT4 Q8 | 27 tok/s 16 tok/s | ~18.5s ~18.5s | |
#171 | Magistral Small | 24B | INT4 Q8 | 26 tok/s 17 tok/s | ~14.5s ~14.6s | |
#172 | Qwen2.5-32B | 32B | INT4 Q8 | 26 tok/s 15 tok/s | ~19.3s ~19.3s | |
#174 | OLMo 3.1 32B Instruct | 32B | INT4 Q8 | 21 tok/s 13 tok/s | ~19.3s ~21.0s | |
#175 | Llama 3.1 70B | 70B | INT4 | 13 tok/s | ~41.8s | |
#176 | DeepSeek-R1 14B | 14B | INT4 Q8 FP16 | 55 tok/s 33 tok/s 17 tok/s | ~8.6s ~8.6s ~8.6s | |
#177 | Ministral 3 14B | 14B | INT4 Q8 FP16 | 40 tok/s 27 tok/s 16 tok/s | ~8.6s ~8.6s ~8.6s | |
#180 | Gemma 3 12B | 12B | INT4 Q8 FP16 | 60 tok/s 37 tok/s 20 tok/s | ~7.4s ~7.4s ~7.4s | |
#183 | Qwen2-72B | 72B | INT4 | 12 tok/s | ~46.8s | |
#184 | Mistral-Small-2501 | 24B | INT4 Q8 FP16 | 34 tok/s 20 tok/s 9 tok/s | ~14.5s ~14.5s ~17.2s | |
#185 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 61 tok/s 43 tok/s 26 tok/s | ~4.9s ~5.0s ~5.0s | |
#186 | Gemma 2 27B | 27B | INT4 Q8 | 30 tok/s 18 tok/s | ~16.3s ~16.3s | |
#187 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 66 tok/s 48 tok/s 29 tok/s | ~4.3s ~4.4s ~4.4s | |
#188 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 174 tok/s 134 tok/s 89 tok/s | ~1.4s ~1.4s ~1.4s | |
#189 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 174 tok/s 134 tok/s 89 tok/s | ~1.4s ~1.4s ~1.4s | |
#190 | Qwen2.5-14B | 14B | INT4 Q8 FP16 | 53 tok/s 32 tok/s 17 tok/s | ~8.6s ~8.6s ~8.6s | |
#191 | OLMo 3.1 32B Think | 32B | INT4 Q8 | 21 tok/s 13 tok/s | ~19.3s ~21.0s | |
#192 | Llama 3 70B | 70B | INT4 | 13 tok/s | ~41.8s | |
#193 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 110 tok/s 74 tok/s 43 tok/s | ~3.2s ~3.2s ~3.2s | |
#195 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 105 tok/s 84 tok/s 57 tok/s | ~1.9s ~2.0s ~2.0s | |
#196 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 84 tok/s 53 tok/s 29 tok/s | ~4.9s ~5.0s ~5.0s | |
#198 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 75 tok/s 47 tok/s 26 tok/s | ~5.6s ~5.6s ~5.6s | |
#199 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 Q8 | 127 tok/s 96 tok/s | ~2.5s ~2.5s | |
#200 | Kimi Linear 48B A3B Instruct | 48B (3B active) | INT4 | 47 tok/s | ~2.8s | |
#201 | Qwen3-4B | 4B | INT4 Q8 FP16 | 127 tok/s 88 tok/s 53 tok/s | ~2.5s ~2.5s ~2.6s | |
#202 | Qwen3-14B | 14B | INT4 Q8 FP16 | 53 tok/s 32 tok/s 17 tok/s | ~8.6s ~8.6s ~8.6s | |
#203 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 127 tok/s 88 tok/s 53 tok/s | ~2.5s ~2.5s ~2.6s | |
#204 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 92 tok/s 59 tok/s 33 tok/s | ~4.3s ~4.3s ~4.4s | |
#205 | OLMo 3 32B Base | 32B | INT4 Q8 | 21 tok/s 13 tok/s | ~19.3s ~21.0s | |
#206 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 234 tok/s 201 tok/s 154 tok/s | ~551 ms ~551 ms ~553 ms | |
#207 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 82 tok/s 52 tok/s 29 tok/s | ~4.9s ~5.0s ~5.0s | |
#207 | Qwen3-8B | 8B | INT4 Q8 FP16 | 82 tok/s 52 tok/s 29 tok/s | ~4.9s ~5.0s ~5.0s | |
#210 | Nemotron 3.5 Lightning | 30B (3B active) | INT4 Q8 | 55 tok/s 50 tok/s | ~2.6s ~2.6s | |
#211 | Command R | 35B | INT4 Q8 | 19 tok/s 12 tok/s | ~21.0s ~22.9s | |
#212 | Llama 3 8B | 8B | INT4 Q8 FP16 | 82 tok/s 52 tok/s 29 tok/s | ~4.9s ~5.0s ~5.0s | |
#213 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 186 tok/s 146 tok/s 99 tok/s | ~1.2s ~1.2s ~1.2s | |
#214 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 259 tok/s 245 tok/s 218 tok/s | ~184 ms ~184 ms ~184 ms | |
#216 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 249 tok/s 220 tok/s 176 tok/s | ~408 ms ~408 ms ~409 ms | |
#217 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 130 tok/s 91 tok/s 55 tok/s | ~2.4s ~2.4s ~2.4s | |
#218 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 90 tok/s 58 tok/s 33 tok/s | ~4.3s ~4.4s ~4.4s | |
#219 | Mixtral-8x7B-v0.1 | 46.7B (7B active) | INT4 Q8 | 81 tok/s 49 tok/s | ~5.0s ~5.9s | |
#220 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 82 tok/s 52 tok/s 29 tok/s | ~4.9s ~5.0s ~5.0s | |
#221 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 195 tok/s 156 tok/s 108 tok/s | ~1.0s ~1.0s ~1.0s | |
#222 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 147 tok/s 106 tok/s 66 tok/s | ~1.9s ~1.9s ~2.0s | |
#223 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 130 tok/s 91 tok/s 55 tok/s | ~2.4s ~2.4s ~2.4s | |
#224 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 105 tok/s 92 tok/s 68 tok/s | ~1.4s ~1.4s ~1.5s | |
#225 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 174 tok/s 134 tok/s 89 tok/s | ~1.4s ~1.4s ~1.4s | |
#226 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 87 tok/s 56 tok/s 31 tok/s | ~4.5s ~4.5s ~4.5s | |
#227 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 220 tok/s 185 tok/s 137 tok/s | ~699 ms ~700 ms ~702 ms | |
#228 | Phi-3-medium | 14B | INT4 Q8 FP16 | 53 tok/s 32 tok/s 17 tok/s | ~8.6s ~8.6s ~8.6s | |
#229 | Yi-34B | 34B | INT4 Q8 | 20 tok/s 12 tok/s | ~20.4s ~22.2s | |
#230 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 66 tok/s 48 tok/s 29 tok/s | ~4.3s ~4.4s ~4.4s | |
#231 | Qwen2-7B | 7B | INT4 Q8 FP16 | 90 tok/s 58 tok/s 33 tok/s | ~4.3s ~4.4s ~4.4s | |
#232 | Phi-3-small | 7B | INT4 Q8 FP16 | 90 tok/s 58 tok/s 33 tok/s | ~4.3s ~4.4s ~4.4s | |
#233 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 87 tok/s 56 tok/s 31 tok/s | ~4.5s ~4.5s ~4.5s | |
#234 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 220 tok/s 185 tok/s 137 tok/s | ~699 ms ~700 ms ~702 ms | |
#236 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 66 tok/s 48 tok/s 29 tok/s | ~4.3s ~4.4s ~4.4s | |
#237 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 183 tok/s 139 tok/s 91 tok/s | ~1.4s ~1.4s ~1.4s | |
#238 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 73 tok/s 54 tok/s 33 tok/s | ~3.7s ~3.8s ~3.8s | |
#239 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 73 tok/s 54 tok/s 33 tok/s | ~3.7s ~3.8s ~3.8s | |
#240 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 73 tok/s 54 tok/s 33 tok/s | ~3.7s ~3.8s ~3.8s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 274 tok/s 256 tok/s 223 tok/s | ~204 ms ~204 ms ~205 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 257 tok/s 231 tok/s 189 tok/s | ~338 ms ~339 ms ~340 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 257 tok/s 231 tok/s 189 tok/s | ~338 ms ~339 ms ~340 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 254 tok/s 239 tok/s 210 tok/s | ~204 ms ~204 ms ~205 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 254 tok/s 239 tok/s 210 tok/s | ~204 ms ~204 ms ~205 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 249 tok/s 220 tok/s 176 tok/s | ~408 ms ~408 ms ~409 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 228 tok/s 190 tok/s 139 tok/s | ~699 ms ~700 ms ~702 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 220 tok/s 185 tok/s 137 tok/s | ~699 ms ~700 ms ~702 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 220 tok/s 185 tok/s 137 tok/s | ~699 ms ~700 ms ~702 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 195 tok/s 156 tok/s 108 tok/s | ~1.0s ~1.0s ~1.0s | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 195 tok/s 156 tok/s 108 tok/s | ~1.0s ~1.0s ~1.0s | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 186 tok/s 146 tok/s 99 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 182 tok/s 142 tok/s 95 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 153 tok/s 109 tok/s 67 tok/s | ~1.9s ~1.9s ~2.0s | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 151 tok/s 132 tok/s 99 tok/s | ~893 ms ~894 ms ~896 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 151 tok/s 132 tok/s 99 tok/s | ~893 ms ~894 ms ~896 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 151 tok/s 132 tok/s 99 tok/s | ~893 ms ~894 ms ~896 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 FP16 | 149 tok/s 113 tok/s 73 tok/s | ~1.9s ~1.9s ~1.9s | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 148 tok/s 107 tok/s 66 tok/s | ~1.9s ~1.9s ~2.0s | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 147 tok/s 106 tok/s 66 tok/s | ~1.9s ~1.9s ~2.0s | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 147 tok/s 106 tok/s 66 tok/s | ~1.9s ~1.9s ~2.0s | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 147 tok/s 106 tok/s 66 tok/s | ~1.9s ~1.9s ~2.0s | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 147 tok/s 106 tok/s 66 tok/s | ~1.9s ~1.9s ~2.0s | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 147 tok/s 106 tok/s 66 tok/s | ~1.9s ~1.9s ~2.0s | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 147 tok/s 106 tok/s 66 tok/s | ~1.9s ~1.9s ~2.0s | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 Q8 FP16 | 139 tok/s 108 tok/s 64 tok/s | ~2.2s ~2.2s ~2.5s | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 Q8 FP16 | 132 tok/s 99 tok/s 60 tok/s | ~2.4s ~2.4s ~2.6s | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 Q8 FP16 | 132 tok/s 99 tok/s 60 tok/s | ~2.4s ~2.4s ~2.6s | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 Q8 | 128 tok/s 97 tok/s | ~2.5s ~2.5s | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 Q8 | 128 tok/s 97 tok/s | ~2.5s ~2.5s | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 127 tok/s 88 tok/s 53 tok/s | ~2.5s ~2.5s ~2.6s | |
- | Hy-Memory 30B A3B | 30B (3B active) | INT4 Q8 | 127 tok/s 96 tok/s | ~2.5s ~2.5s | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 Q8 | 127 tok/s 96 tok/s | ~2.5s ~2.5s | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 127 tok/s 88 tok/s 53 tok/s | ~2.5s ~2.5s ~2.6s | |
- | MiniCPM-V 4.7 35B A3B | 35B (3B active) | INT4 Q8 | 125 tok/s 95 tok/s | ~2.6s ~2.6s | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 122 tok/s 103 tok/s 74 tok/s | ~1.4s ~1.4s ~1.4s | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 110 tok/s 89 tok/s 61 tok/s | ~1.8s ~1.8s ~1.8s | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 105 tok/s 84 tok/s 57 tok/s | ~1.9s ~2.0s ~2.0s | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 105 tok/s 84 tok/s 57 tok/s | ~1.9s ~2.0s ~2.0s | |
- | AliceAI Foundation 80B A3B Base | 80B (3B active) | INT4 | 99 tok/s | ~3.8s | |
- | Kolibri 1 | 78B (3.5B active) | INT4 | 94 tok/s | ~4.1s | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 93 tok/s 59 tok/s 33 tok/s | ~4.3s ~4.3s ~4.4s | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 90 tok/s 58 tok/s 33 tok/s | ~4.3s ~4.4s ~4.4s | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 90 tok/s 58 tok/s 33 tok/s | ~4.3s ~4.4s ~4.4s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 87 tok/s 56 tok/s 31 tok/s | ~4.5s ~4.5s ~4.5s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 FP16 | 84 tok/s 53 tok/s 29 tok/s | ~4.9s ~5.0s ~5.0s | |
- | LensVLM 9B | 9B | INT4 Q8 FP16 | 75 tok/s 47 tok/s 26 tok/s | ~5.6s ~5.6s ~5.6s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 FP16 | 75 tok/s 47 tok/s 26 tok/s | ~5.6s ~5.6s ~5.6s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 73 tok/s 54 tok/s 33 tok/s | ~3.7s ~3.8s ~3.8s | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 73 tok/s 54 tok/s 33 tok/s | ~3.7s ~3.8s ~3.8s | |
- | Falcon3-10B | 10B | INT4 Q8 FP16 | 69 tok/s 43 tok/s 24 tok/s | ~6.2s ~6.2s ~6.2s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 Q8 FP16 | 69 tok/s 61 tok/s 45 tok/s | ~2.3s ~2.3s ~2.3s | |
- | Falcon2-11B | 11B | INT4 Q8 FP16 | 67 tok/s 41 tok/s 22 tok/s | ~6.8s ~6.8s ~6.8s | |
- | Hunyuan Lite | 7B | INT4 Q8 FP16 | 66 tok/s 48 tok/s 29 tok/s | ~4.3s ~4.4s ~4.4s | |
- | OLMo 3 7B Base | 7B | INT4 Q8 FP16 | 66 tok/s 48 tok/s 29 tok/s | ~4.3s ~4.4s ~4.4s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 FP16 | 66 tok/s 48 tok/s 29 tok/s | ~4.4s ~4.4s ~4.4s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 FP16 | 66 tok/s 48 tok/s 29 tok/s | ~4.4s ~4.4s ~4.4s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 FP16 | 61 tok/s 43 tok/s 26 tok/s | ~4.9s ~5.0s ~5.0s | |
- | Typhoon-2-8B | 8B | INT4 Q8 FP16 | 61 tok/s 43 tok/s 26 tok/s | ~4.9s ~5.0s ~5.0s | |
- | GLM-4-9B | 9B | INT4 Q8 FP16 | 56 tok/s 39 tok/s 23 tok/s | ~5.6s ~5.6s ~5.6s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 FP16 | 56 tok/s 39 tok/s 23 tok/s | ~5.6s ~5.6s ~5.6s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 FP16 | 56 tok/s 39 tok/s 23 tok/s | ~5.6s ~5.6s ~5.6s | |
- | Yi-9B | 9B | INT4 Q8 FP16 | 56 tok/s 39 tok/s 23 tok/s | ~5.6s ~5.6s ~5.6s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 FP16 | 55 tok/s 39 tok/s 23 tok/s | ~5.7s ~5.7s ~5.7s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 FP16 | 55 tok/s 39 tok/s 23 tok/s | ~5.7s ~5.7s ~5.7s | |
- | GreenMind-14B-R1 | 14B | INT4 Q8 FP16 | 40 tok/s 27 tok/s 16 tok/s | ~8.6s ~8.6s ~8.6s | |
- | AREX-2 | 27B | INT4 Q8 | 30 tok/s 18 tok/s | ~16.3s ~16.3s | |
- | PPLX Decider v1 27B | 27B | INT4 Q8 | 30 tok/s 18 tok/s | ~16.3s ~16.3s | |
- | PPLX Decider v1.1 27B | 27B | INT4 Q8 | 30 tok/s 18 tok/s | ~16.3s ~16.3s | |
- | Agnes 3.0 Flash | 33B | INT4 Q8 | 26 tok/s 15 tok/s | ~19.8s ~19.9s | |
- | Falcon-40B | 40B | INT4 Q8 | 22 tok/s 12 tok/s | ~24.0s ~26.1s | |
- | Kimi-Dev-72B | 72B | INT4 | 9 tok/s | ~50.6s | |
- | Typhoon-2-70B | 70B | INT4 | 9 tok/s | ~49.2s | |
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 M5 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 614 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 136 tok/s on an 8B Q4 model and 16 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