Apple M2 Ultra (64GB)
The Apple M2 Ultra (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 800 GB/s unified memory bandwidth.
Memory
64 GB
Usable Memory Ceiling
48 GB (75% usable budget)
Bandwidth
800 GB/s
Max Inference Class
32B Models (Q4)
TDP
230W
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 M2 Ultra (64GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on Apple M2 Ultra (64GB).
Sort by:
Context:
KV Cache:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#36 | Qwen 3.8 27B | 27B | INT4 Q8 | 39 tok/s 23 tok/s | ~10.0s ~10.0s | |
#80 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 Q8 | 129 tok/s 97 tok/s | ~2.0s ~2.0s | |
#86 | Qwen3.5-27B | 27B | INT4 Q8 | 39 tok/s 23 tok/s | ~10.0s ~10.0s | |
#93 | Sarvam-30B | 32B (2.4B active) | INT4 Q8 | 157 tok/s 127 tok/s | ~1.4s ~1.4s | |
#99 | Muse Glimmer 30B | 30B | INT4 Q8 | 35 tok/s 21 tok/s | ~11.0s ~11.1s | |
#102 | Phi-4 Reasoning Plus | 14B | INT4 Q8 FP16 | 50 tok/s 34 tok/s 20 tok/s | ~5.2s ~5.3s ~5.3s | |
#103 | Qwen3.6 35B A3B | 35B (3B active) | INT4 Q8 | 145 tok/s 113 tok/s | ~1.6s ~1.6s | |
#105 | MiMo V2 Flash | 15B (309B active) | INT4 Q8 FP16 | 4 tok/s 2 tok/s 1 tok/s | ~108.9s ~109.2s ~109.6s | |
#110 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 Q8 | 136 tok/s 102 tok/s | ~1.8s ~1.8s | |
#117 | Nemotron 3.5 Bolt 74B A9B | 74B | INT4 | 15 tok/s | ~29.4s | |
#120 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 Q8 | 145 tok/s 113 tok/s | ~1.6s ~1.6s | |
#121 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 91 tok/s 59 tok/s 33 tok/s | ~3.4s ~3.4s ~3.4s | |
#127 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
#130 | Gemma 4 12B | 11.95B | INT4 Q8 FP16 | 56 tok/s 39 tok/s 23 tok/s | ~4.5s ~4.5s ~4.5s | |
#136 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 147 tok/s 105 tok/s 65 tok/s | ~1.6s ~1.6s ~1.6s | |
#139 | GPT-OSS 20B | 21B (3.6B active) | INT4 Q8 FP16 | 75 tok/s 66 tok/s 44 tok/s | ~1.7s ~1.7s ~2.0s | |
#140 | GLM-4V | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 30 tok/s | ~3.4s ~3.4s ~3.4s | |
#145 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 34 tok/s 20 tok/s 11 tok/s | ~10.7s ~10.7s ~10.8s | |
#150 | Qwen3-30B-A3B | 30B (3B active) | INT4 Q8 | 147 tok/s 114 tok/s | ~1.6s ~1.6s | |
#152 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#157 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#158 | Mistral Large 3 | 41B (675B active) | INT4 | 2 tok/s | ~237.9s | |
#159 | Qwen2.5-72B | 72B | INT4 | 15 tok/s | ~28.6s | |
#161 | GLM-4 | 32B | INT4 Q8 | 26 tok/s 16 tok/s | ~11.8s ~12.8s | |
#162 | DeepSeek-R1 70B | 70B | INT4 | 17 tok/s | ~25.6s | |
#163 | Gemma 3 27B | 27B | INT4 Q8 | 39 tok/s 23 tok/s | ~10.0s ~10.0s | |
#164 | Phi-4 | 14B | INT4 Q8 FP16 | 66 tok/s 41 tok/s 22 tok/s | ~5.2s ~5.2s ~5.3s | |
#165 | Llama 3.3 70B | 70B | INT4 | 16 tok/s | ~25.6s | |
#166 | Qwen3-32B | 32B | INT4 Q8 | 33 tok/s 19 tok/s | ~11.8s ~11.8s | |
#167 | Hunyuan Standard | 52B (389B active) | INT4 | 3 tok/s | ~137.4s | |
#168 | DeepSeek-R1 32B | 32B | INT4 Q8 | 34 tok/s 20 tok/s | ~11.8s ~11.8s | |
#169 | Gemma 4 31B | 30.7B | INT4 Q8 | 35 tok/s 20 tok/s | ~11.3s ~11.3s | |
#171 | Magistral Small | 24B | INT4 Q8 | 33 tok/s 22 tok/s | ~8.9s ~8.9s | |
#172 | Qwen2.5-32B | 32B | INT4 Q8 | 33 tok/s 19 tok/s | ~11.8s ~11.8s | |
#174 | OLMo 3.1 32B Instruct | 32B | INT4 Q8 | 26 tok/s 16 tok/s | ~11.8s ~12.8s | |
#175 | Llama 3.1 70B | 70B | INT4 | 16 tok/s | ~25.6s | |
#176 | DeepSeek-R1 14B | 14B | INT4 Q8 FP16 | 68 tok/s 41 tok/s 22 tok/s | ~5.2s ~5.2s ~5.3s | |
#177 | Ministral 3 14B | 14B | INT4 Q8 FP16 | 50 tok/s 34 tok/s 20 tok/s | ~5.2s ~5.3s ~5.3s | |
#180 | Gemma 3 12B | 12B | INT4 Q8 FP16 | 74 tok/s 46 tok/s 26 tok/s | ~4.5s ~4.5s ~4.5s | |
#183 | Qwen2-72B | 72B | INT4 | 15 tok/s | ~28.6s | |
#184 | Mistral-Small-2501 | 24B | INT4 Q8 FP16 | 43 tok/s 25 tok/s 12 tok/s | ~8.9s ~8.9s ~10.5s | |
#185 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 75 tok/s 54 tok/s 33 tok/s | ~3.0s ~3.0s ~3.0s | |
#186 | Gemma 2 27B | 27B | INT4 Q8 | 39 tok/s 23 tok/s | ~10.0s ~10.0s | |
#187 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 81 tok/s 60 tok/s 37 tok/s | ~2.7s ~2.7s ~2.7s | |
#188 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 194 tok/s 154 tok/s 106 tok/s | ~829 ms ~830 ms ~833 ms | |
#189 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 194 tok/s 154 tok/s 106 tok/s | ~829 ms ~830 ms ~833 ms | |
#190 | Qwen2.5-14B | 14B | INT4 Q8 FP16 | 66 tok/s 41 tok/s 22 tok/s | ~5.2s ~5.2s ~5.3s | |
#191 | OLMo 3.1 32B Think | 32B | INT4 Q8 | 26 tok/s 16 tok/s | ~11.8s ~12.8s | |
#192 | Llama 3 70B | 70B | INT4 | 16 tok/s | ~25.6s | |
#193 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 129 tok/s 90 tok/s 54 tok/s | ~2.0s ~2.0s ~2.0s | |
#195 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 124 tok/s 101 tok/s 70 tok/s | ~1.2s ~1.2s ~1.2s | |
#196 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 101 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#198 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 91 tok/s 59 tok/s 33 tok/s | ~3.4s ~3.4s ~3.4s | |
#199 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 Q8 | 147 tok/s 114 tok/s | ~1.6s ~1.6s | |
#200 | Kimi Linear 48B A3B Instruct | 48B (3B active) | INT4 | 59 tok/s | ~1.7s | |
#201 | Qwen3-4B | 4B | INT4 Q8 FP16 | 147 tok/s 105 tok/s 65 tok/s | ~1.6s ~1.6s ~1.6s | |
#202 | Qwen3-14B | 14B | INT4 Q8 FP16 | 66 tok/s 41 tok/s 22 tok/s | ~5.2s ~5.2s ~5.3s | |
#203 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 147 tok/s 105 tok/s 65 tok/s | ~1.6s ~1.6s ~1.6s | |
#204 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 109 tok/s 72 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
#205 | OLMo 3 32B Base | 32B | INT4 Q8 | 26 tok/s 16 tok/s | ~11.8s ~12.8s | |
#206 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 247 tok/s 218 tok/s 174 tok/s | ~340 ms ~340 ms ~341 ms | |
#207 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#207 | Qwen3-8B | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#210 | Nemotron 3.5 Lightning | 30B (3B active) | INT4 Q8 | 68 tok/s 62 tok/s | ~1.6s ~1.6s | |
#211 | Command R | 35B | INT4 Q8 | 24 tok/s 15 tok/s | ~12.8s ~14.0s | |
#212 | Llama 3 8B | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#213 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 204 tok/s 166 tok/s 117 tok/s | ~710 ms ~711 ms ~713 ms | |
#214 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 268 tok/s 257 tok/s 233 tok/s | ~115 ms ~116 ms ~116 ms | |
#216 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 259 tok/s 235 tok/s 195 tok/s | ~252 ms ~253 ms ~253 ms | |
#217 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 150 tok/s 109 tok/s 68 tok/s | ~1.5s ~1.5s ~1.5s | |
#218 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
#219 | Mixtral-8x7B-v0.1 | 46.7B (7B active) | INT4 Q8 | 97 tok/s 60 tok/s | ~3.1s ~3.6s | |
#220 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#221 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 212 tok/s 175 tok/s 126 tok/s | ~628 ms ~629 ms ~631 ms | |
#222 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 167 tok/s 125 tok/s 81 tok/s | ~1.2s ~1.2s ~1.2s | |
#223 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 150 tok/s 109 tok/s 68 tok/s | ~1.5s ~1.5s ~1.5s | |
#224 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 124 tok/s 109 tok/s 83 tok/s | ~888 ms ~889 ms ~892 ms | |
#225 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 194 tok/s 154 tok/s 106 tok/s | ~829 ms ~830 ms ~833 ms | |
#226 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 105 tok/s 69 tok/s 40 tok/s | ~2.8s ~2.8s ~2.8s | |
#227 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 235 tok/s 203 tok/s 157 tok/s | ~431 ms ~431 ms ~433 ms | |
#228 | Phi-3-medium | 14B | INT4 Q8 FP16 | 66 tok/s 41 tok/s 22 tok/s | ~5.2s ~5.2s ~5.3s | |
#229 | Yi-34B | 34B | INT4 Q8 | 25 tok/s 15 tok/s | ~12.5s ~13.6s | |
#230 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 81 tok/s 60 tok/s 37 tok/s | ~2.7s ~2.7s ~2.7s | |
#231 | Qwen2-7B | 7B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
#232 | Phi-3-small | 7B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
#233 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 105 tok/s 69 tok/s 40 tok/s | ~2.8s ~2.8s ~2.8s | |
#234 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 235 tok/s 203 tok/s 157 tok/s | ~431 ms ~431 ms ~433 ms | |
#236 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 81 tok/s 60 tok/s 37 tok/s | ~2.7s ~2.7s ~2.7s | |
#237 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 201 tok/s 159 tok/s 108 tok/s | ~829 ms ~830 ms ~833 ms | |
#238 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 89 tok/s 67 tok/s 42 tok/s | ~2.3s ~2.3s ~2.3s | |
#239 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 89 tok/s 67 tok/s 42 tok/s | ~2.3s ~2.3s ~2.3s | |
#240 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 89 tok/s 67 tok/s 42 tok/s | ~2.3s ~2.3s ~2.3s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 280 tok/s 265 tok/s 237 tok/s | ~128 ms ~128 ms ~128 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 266 tok/s 245 tok/s 207 tok/s | ~210 ms ~210 ms ~211 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 266 tok/s 245 tok/s 207 tok/s | ~210 ms ~210 ms ~211 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 264 tok/s 252 tok/s 226 tok/s | ~128 ms ~128 ms ~129 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 264 tok/s 252 tok/s 226 tok/s | ~128 ms ~128 ms ~129 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 259 tok/s 235 tok/s 195 tok/s | ~252 ms ~253 ms ~253 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 242 tok/s 208 tok/s 159 tok/s | ~430 ms ~431 ms ~433 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 235 tok/s 203 tok/s 157 tok/s | ~431 ms ~431 ms ~433 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 235 tok/s 203 tok/s 157 tok/s | ~431 ms ~431 ms ~433 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 212 tok/s 175 tok/s 126 tok/s | ~628 ms ~629 ms ~631 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 212 tok/s 175 tok/s 126 tok/s | ~628 ms ~629 ms ~631 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 204 tok/s 166 tok/s 117 tok/s | ~710 ms ~711 ms ~713 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 201 tok/s 162 tok/s 113 tok/s | ~747 ms ~748 ms ~751 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 173 tok/s 129 tok/s 82 tok/s | ~1.2s ~1.2s ~1.2s | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 171 tok/s 152 tok/s 118 tok/s | ~549 ms ~550 ms ~552 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 171 tok/s 152 tok/s 118 tok/s | ~549 ms ~550 ms ~552 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 171 tok/s 152 tok/s 118 tok/s | ~549 ms ~550 ms ~552 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 FP16 | 169 tok/s 132 tok/s 89 tok/s | ~1.2s ~1.2s ~1.2s | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 168 tok/s 126 tok/s 81 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 167 tok/s 125 tok/s 81 tok/s | ~1.2s ~1.2s ~1.2s | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 167 tok/s 125 tok/s 81 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 167 tok/s 125 tok/s 81 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 167 tok/s 125 tok/s 81 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 167 tok/s 125 tok/s 81 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 167 tok/s 125 tok/s 81 tok/s | ~1.2s ~1.2s ~1.2s | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 Q8 FP16 | 159 tok/s 127 tok/s 78 tok/s | ~1.3s ~1.3s ~1.6s | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 Q8 FP16 | 152 tok/s 117 tok/s 73 tok/s | ~1.5s ~1.5s ~1.6s | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 Q8 FP16 | 152 tok/s 117 tok/s 73 tok/s | ~1.5s ~1.5s ~1.6s | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 Q8 | 148 tok/s 115 tok/s | ~1.5s ~1.5s | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 Q8 | 148 tok/s 115 tok/s | ~1.5s ~1.5s | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 147 tok/s 105 tok/s 65 tok/s | ~1.6s ~1.6s ~1.6s | |
- | Hy-Memory 30B A3B | 30B (3B active) | INT4 Q8 | 147 tok/s 114 tok/s | ~1.6s ~1.6s | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 Q8 | 147 tok/s 114 tok/s | ~1.6s ~1.6s | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 147 tok/s 105 tok/s 65 tok/s | ~1.6s ~1.6s ~1.6s | |
- | MiniCPM-V 4.7 35B A3B | 35B (3B active) | INT4 Q8 | 145 tok/s 113 tok/s | ~1.6s ~1.6s | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 142 tok/s 122 tok/s 90 tok/s | ~831 ms ~832 ms ~835 ms | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 129 tok/s 107 tok/s 75 tok/s | ~1.1s ~1.1s ~1.1s | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 124 tok/s 101 tok/s 70 tok/s | ~1.2s ~1.2s ~1.2s | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 124 tok/s 101 tok/s 70 tok/s | ~1.2s ~1.2s ~1.2s | |
- | AliceAI Foundation 80B A3B Base | 80B (3B active) | INT4 | 117 tok/s | ~2.3s | |
- | Kolibri 1 | 78B (3.5B active) | INT4 | 112 tok/s | ~2.5s | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 111 tok/s 73 tok/s 42 tok/s | ~2.7s ~2.7s ~2.7s | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 105 tok/s 69 tok/s 40 tok/s | ~2.8s ~2.8s ~2.8s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 FP16 | 101 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
- | LensVLM 9B | 9B | INT4 Q8 FP16 | 91 tok/s 59 tok/s 33 tok/s | ~3.4s ~3.4s ~3.4s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 FP16 | 91 tok/s 59 tok/s 33 tok/s | ~3.4s ~3.4s ~3.4s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 89 tok/s 67 tok/s 42 tok/s | ~2.3s ~2.3s ~2.3s | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 89 tok/s 67 tok/s 42 tok/s | ~2.3s ~2.3s ~2.3s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 Q8 FP16 | 85 tok/s 75 tok/s 56 tok/s | ~1.4s ~1.4s ~1.4s | |
- | Falcon3-10B | 10B | INT4 Q8 FP16 | 84 tok/s 54 tok/s 30 tok/s | ~3.8s ~3.8s ~3.8s | |
- | Falcon2-11B | 11B | INT4 Q8 FP16 | 82 tok/s 51 tok/s 28 tok/s | ~4.1s ~4.1s ~4.2s | |
- | Hunyuan Lite | 7B | INT4 Q8 FP16 | 81 tok/s 60 tok/s 37 tok/s | ~2.7s ~2.7s ~2.7s | |
- | OLMo 3 7B Base | 7B | INT4 Q8 FP16 | 81 tok/s 60 tok/s 37 tok/s | ~2.7s ~2.7s ~2.7s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 FP16 | 81 tok/s 59 tok/s 37 tok/s | ~2.7s ~2.7s ~2.7s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 FP16 | 81 tok/s 59 tok/s 37 tok/s | ~2.7s ~2.7s ~2.7s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 FP16 | 75 tok/s 54 tok/s 33 tok/s | ~3.0s ~3.0s ~3.0s | |
- | Typhoon-2-8B | 8B | INT4 Q8 FP16 | 75 tok/s 54 tok/s 33 tok/s | ~3.0s ~3.0s ~3.0s | |
- | GLM-4-9B | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 30 tok/s | ~3.4s ~3.4s ~3.4s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 30 tok/s | ~3.4s ~3.4s ~3.4s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 30 tok/s | ~3.4s ~3.4s ~3.4s | |
- | Yi-9B | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 30 tok/s | ~3.4s ~3.4s ~3.4s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 FP16 | 68 tok/s 49 tok/s 29 tok/s | ~3.5s ~3.5s ~3.5s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 FP16 | 68 tok/s 49 tok/s 29 tok/s | ~3.5s ~3.5s ~3.5s | |
- | GreenMind-14B-R1 | 14B | INT4 Q8 FP16 | 50 tok/s 34 tok/s 20 tok/s | ~5.2s ~5.3s ~5.3s | |
- | AREX-2 | 27B | INT4 Q8 | 39 tok/s 23 tok/s | ~10.0s ~10.0s | |
- | PPLX Decider v1 27B | 27B | INT4 Q8 | 39 tok/s 23 tok/s | ~10.0s ~10.0s | |
- | PPLX Decider v1.1 27B | 27B | INT4 Q8 | 39 tok/s 23 tok/s | ~10.0s ~10.0s | |
- | Agnes 3.0 Flash | 33B | INT4 Q8 | 32 tok/s 19 tok/s | ~12.1s ~12.1s | |
- | Falcon-40B | 40B | INT4 Q8 | 28 tok/s 15 tok/s | ~14.6s ~15.9s | |
- | Typhoon-2-70B | 70B | INT4 | 12 tok/s | ~30.1s | |
- | Kimi-Dev-72B | 72B | INT4 | 11 tok/s | ~30.9s | |
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 M2 Ultra (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 800 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 178 tok/s on an 8B Q4 model and 21 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