趋近智
Apple M2 Ultra (192GB)
Apple M2 Ultra (192GB) 采用统一内存架构。为了在避免系统内存压力的情况下确保本地大模型稳定推理，本评测以 75% 可用配额（144 GB）及 800 GB/s 统一内存带宽进行建模。
总显存
192 GB
可用显存上限
144 GB （75% 可用预算）
显存带宽
800 GB/s
最大推理模型级别
70B+ 模型 (Q4)
热设计功耗
230W
显存占用随上下文长度变化曲线
随上下文长度增长的显存需求评估。当曲线超过参考线时将导致显存不足（OOM）。
量化精度:
Apple M2 Ultra (192GB) 最佳运行大模型与速度矩阵
主流开源大模型在 Apple M2 Ultra (192GB) 上的推理速度、显存兼容性与生成吞吐表现。
排序:
上下文长度:
KV 缓存:
| 排名 | 模型 | 参数量 | 量化精度 | 预估 TPS | TTFT | 可运行 |
|---|---|---|---|---|---|---|
#30 | DeepSeek-V4-Flash-Vision-Exp | 290.9B (20.4B active) | INT4 | 46 tok/s | ~8.5s | |
#33 | Qwen 3.8 27B | 27B | INT4 Q8 FP16 | 39 tok/s 23 tok/s 12 tok/s | ~10.0s ~10.0s ~10.0s | |
#41 | Qwen 3.8 Flash | 176B (6B active) | INT4 | 122 tok/s | ~2.1s | |
#42 | DeepSeek-V4-Flash | 284B (13B active) | INT4 | 65 tok/s | ~5.4s | |
#48 | Agnes 3.0 Flash | 33B | INT4 Q8 FP16 | 32 tok/s 19 tok/s 10 tok/s | ~12.1s ~12.1s ~12.2s | |
#61 | Sarvam-105B | 106B (10.3B active) | INT4 Q8 | 82 tok/s 52 tok/s | ~5.1s ~5.1s | |
#72 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 Q8 FP16 | 129 tok/s 97 tok/s 62 tok/s | ~2.0s ~2.0s ~2.0s | |
#75 | Ling 3.0 Flash VL | 124B (5.5B active) | INT4 Q8 | 119 tok/s 79 tok/s | ~3.6s ~4.0s | |
#82 | Qwen3 235B A22B Thinking | 235B (22B active) | INT4 | 14 tok/s | ~11.8s | |
#83 | Qwen3.5-27B | 27B | INT4 Q8 FP16 | 39 tok/s 23 tok/s 12 tok/s | ~10.0s ~10.0s ~10.0s | |
#84 | Qwen3.5-122B-A10B | 122B (10B active) | INT4 Q8 | 66 tok/s 44 tok/s | ~5.2s ~5.7s | |
#92 | Sarvam-30B | 32B (2.4B active) | INT4 Q8 FP16 | 157 tok/s 127 tok/s 88 tok/s | ~1.4s ~1.4s ~1.4s | |
#94 | Qwen3.6 35B A3B | 35B (3B active) | INT4 Q8 FP16 | 145 tok/s 113 tok/s 76 tok/s | ~1.6s ~1.6s ~1.6s | |
#96 | Muse Glimmer 30B | 30B | INT4 Q8 FP16 | 35 tok/s 21 tok/s 11 tok/s | ~11.0s ~11.1s ~11.1s | |
#100 | Phi-4 Reasoning Plus | 14B | INT4 Q8 FP16 | 50 tok/s 34 tok/s 20 tok/s | ~5.2s ~5.3s ~5.3s | |
#101 | MiMo V2 Flash | 15B (309B active) | INT4 Q8 FP16 | 4 tok/s 2 tok/s 1 tok/s | ~108.9s ~109.2s ~109.6s | |
#106 | GLM-4.5-Air | 106B (12B active) | INT4 Q8 | 25 tok/s 21 tok/s | ~5.7s ~6.2s | |
#108 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 Q8 FP16 | 136 tok/s 102 tok/s 65 tok/s | ~1.8s ~1.8s ~1.8s | |
#109 | Gemma 4 12B | 11.95B | INT4 Q8 FP16 | 56 tok/s 39 tok/s 23 tok/s | ~4.5s ~4.5s ~4.5s | |
#111 | MiniMax M2 | 229B (10B active) | INT4 | 17 tok/s | ~6.8s | |
#113 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 91 tok/s 59 tok/s 33 tok/s | ~3.4s ~3.4s ~3.4s | |
#114 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 Q8 FP16 | 145 tok/s 113 tok/s 76 tok/s | ~1.6s ~1.6s ~1.6s | |
#114 | Ling 3.0 Flash | 124B (5.1B active) | INT4 Q8 | 123 tok/s 83 tok/s | ~3.5s ~3.8s | |
#118 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
#119 | Step 3.5 Flash | 196.81B (11B active) | INT4 | 61 tok/s | ~5.8s | |
#126 | Qwen3 Next 80B A3B | 80B (79B active) | INT4 Q8 | 12 tok/s 7 tok/s | ~28.9s ~28.9s | |
#128 | 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 | |
#129 | Gemma 4 31B | 30.7B | INT4 Q8 FP16 | 35 tok/s 20 tok/s 11 tok/s | ~11.3s ~11.3s ~11.4s | |
#130 | GPT-OSS 120B | 117B (5.1B active) | INT4 Q8 | 27 tok/s 25 tok/s | ~3.5s ~3.8s | |
#131 | Nemotron 3.5 Lightning | 30B (3B active) | INT4 Q8 FP16 | 68 tok/s 62 tok/s 49 tok/s | ~1.6s ~1.6s ~1.6s | |
#132 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 147 tok/s 105 tok/s 65 tok/s | ~1.6s ~1.6s ~1.6s | |
#133 | Qwen3-30B-A3B | 30B (3B active) | INT4 Q8 FP16 | 147 tok/s 114 tok/s 76 tok/s | ~1.6s ~1.6s ~1.6s | |
#136 | GPT-OSS 20B | 21B (3.6B active) | INT4 Q8 FP16 | 75 tok/s 66 tok/s 49 tok/s | ~1.7s ~1.7s ~1.7s | |
#139 | Qwen3-235B-A22B | 235B (22B active) | INT4 | 36 tok/s | ~10.9s | |
#144 | Mistral Medium 3.5 128B | 128B | INT4 Q8 | 7 tok/s 4 tok/s | ~46.7s ~55.0s | |
#146 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#150 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#151 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 Q8 FP16 | 147 tok/s 114 tok/s 76 tok/s | ~1.6s ~1.6s ~1.6s | |
#153 | Qwen3-32B | 32B | INT4 Q8 FP16 | 33 tok/s 19 tok/s 10 tok/s | ~11.8s ~11.8s ~11.8s | |
#154 | Qwen2.5-72B | 72B | INT4 Q8 FP16 | 16 tok/s 9 tok/s 4 tok/s | ~26.3s ~26.3s ~31.1s | |
#155 | Mistral Large 3 | 41B (675B active) | INT4 Q8 FP16 | 2 tok/s 1 tok/s 1 tok/s | ~237.9s ~238.3s ~239.3s | |
#156 | GLM-4 | 32B | INT4 Q8 FP16 | 26 tok/s 17 tok/s 9 tok/s | ~11.8s ~11.8s ~11.8s | |
#157 | DeepSeek-R1 70B | 70B | INT4 Q8 FP16 | 17 tok/s 9 tok/s 4 tok/s | ~25.6s ~25.6s ~30.2s | |
#158 | GLM-4V | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 30 tok/s | ~3.4s ~3.4s ~3.4s | |
#159 | Gemma 3 27B | 27B | INT4 Q8 FP16 | 39 tok/s 23 tok/s 12 tok/s | ~10.0s ~10.0s ~10.0s | |
#160 | Phi-4 | 14B | INT4 Q8 FP16 | 66 tok/s 41 tok/s 22 tok/s | ~5.2s ~5.2s ~5.3s | |
#161 | Llama 3.3 70B | 70B | INT4 Q8 FP16 | 16 tok/s 9 tok/s 4 tok/s | ~25.6s ~25.6s ~30.2s | |
#162 | DeepSeek-R1 32B | 32B | INT4 Q8 FP16 | 34 tok/s 20 tok/s 10 tok/s | ~11.8s ~11.8s ~11.8s | |
#163 | Hunyuan Standard | 52B (389B active) | INT4 Q8 FP16 | 3 tok/s 2 tok/s 1 tok/s | ~137.4s ~137.7s ~138.2s | |
#164 | Qwen2.5-32B | 32B | INT4 Q8 FP16 | 33 tok/s 19 tok/s 10 tok/s | ~11.8s ~11.8s ~11.8s | |
#168 | Magistral Small | 24B | INT4 Q8 FP16 | 33 tok/s 22 tok/s 12 tok/s | ~8.9s ~8.9s ~8.9s | |
#169 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 81 tok/s 60 tok/s 37 tok/s | ~2.7s ~2.7s ~2.7s | |
#170 | OLMo 3.1 32B Instruct | 32B | INT4 Q8 FP16 | 26 tok/s 17 tok/s 9 tok/s | ~11.8s ~11.8s ~11.8s | |
#171 | Llama 3.1 70B | 70B | INT4 Q8 FP16 | 16 tok/s 9 tok/s 4 tok/s | ~25.6s ~25.6s ~30.2s | |
#172 | DeepSeek-R1 14B | 14B | INT4 Q8 FP16 | 68 tok/s 41 tok/s 22 tok/s | ~5.2s ~5.2s ~5.3s | |
#173 | Ministral 3 14B | 14B | INT4 Q8 FP16 | 50 tok/s 34 tok/s 20 tok/s | ~5.2s ~5.3s ~5.3s | |
#174 | Mistral-Large-2407 | 123B | INT4 Q8 | 9 tok/s 5 tok/s | ~44.9s ~48.9s | |
#175 | Llama 4 Scout | 109B (17B active) | INT4 Q8 | 49 tok/s 32 tok/s | ~7.5s ~7.5s | |
#177 | Gemma 3 12B | 12B | INT4 Q8 FP16 | 74 tok/s 46 tok/s 26 tok/s | ~4.5s ~4.5s ~4.5s | |
#178 | Command A | 111B | INT4 Q8 | 8 tok/s 5 tok/s | ~40.6s ~44.2s | |
#179 | Qwen2-72B | 72B | INT4 Q8 FP16 | 16 tok/s 9 tok/s 4 tok/s | ~26.3s ~26.3s ~31.1s | |
#180 | OLMo 3 32B Base | 32B | INT4 Q8 FP16 | 26 tok/s 17 tok/s 9 tok/s | ~11.8s ~11.8s ~11.8s | |
#181 | Mistral-Small-2501 | 24B | INT4 Q8 FP16 | 43 tok/s 25 tok/s 13 tok/s | ~8.9s ~8.9s ~8.9s | |
#182 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 75 tok/s 54 tok/s 33 tok/s | ~3.0s ~3.0s ~3.0s | |
#183 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 194 tok/s 154 tok/s 106 tok/s | ~829 ms ~830 ms ~833 ms | |
#184 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 194 tok/s 154 tok/s 106 tok/s | ~829 ms ~830 ms ~833 ms | |
#185 | Qwen2.5-14B | 14B | INT4 Q8 FP16 | 66 tok/s 41 tok/s 22 tok/s | ~5.2s ~5.2s ~5.3s | |
#186 | Gemma 2 27B | 27B | INT4 Q8 FP16 | 39 tok/s 23 tok/s 12 tok/s | ~10.0s ~10.0s ~10.0s | |
#187 | OLMo 3.1 32B Think | 32B | INT4 Q8 FP16 | 26 tok/s 17 tok/s 9 tok/s | ~11.8s ~11.8s ~11.8s | |
#188 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 129 tok/s 90 tok/s 54 tok/s | ~2.0s ~2.0s ~2.0s | |
#189 | Qwen3-4B | 4B | INT4 Q8 FP16 | 147 tok/s 105 tok/s 65 tok/s | ~1.6s ~1.6s ~1.6s | |
#190 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 101 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#191 | Llama 3 70B | 70B | INT4 Q8 FP16 | 16 tok/s 9 tok/s 4 tok/s | ~25.6s ~25.6s ~30.2s | |
#192 | Command R Plus | 104B | INT4 Q8 | 9 tok/s 5 tok/s | ~38.0s ~41.4s | |
#193 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 124 tok/s 101 tok/s 70 tok/s | ~1.2s ~1.2s ~1.2s | |
#195 | Qwen3-14B | 14B | INT4 Q8 FP16 | 66 tok/s 41 tok/s 22 tok/s | ~5.2s ~5.2s ~5.3s | |
#196 | Kimi Linear 48B A3B Instruct | 48B (3B active) | INT4 Q8 FP16 | 59 tok/s 55 tok/s 44 tok/s | ~1.7s ~1.7s ~1.7s | |
#197 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 91 tok/s 59 tok/s 33 tok/s | ~3.4s ~3.4s ~3.4s | |
#198 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
#199 | Qwen3-8B | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#200 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 147 tok/s 105 tok/s 65 tok/s | ~1.6s ~1.6s ~1.6s | |
#201 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 109 tok/s 72 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
#202 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#203 | Mixtral-8x22B-v0.1 | 176B (22B active) | INT4 | 40 tok/s | ~9.4s | |
#204 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 204 tok/s 166 tok/s 117 tok/s | ~710 ms ~711 ms ~713 ms | |
#205 | Command R | 35B | INT4 Q8 FP16 | 24 tok/s 16 tok/s 9 tok/s | ~12.8s ~12.9s ~12.9s | |
#206 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 268 tok/s 257 tok/s 233 tok/s | ~115 ms ~116 ms ~116 ms | |
#208 | Llama 3 8B | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#209 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 259 tok/s 235 tok/s 195 tok/s | ~252 ms ~253 ms ~253 ms | |
#210 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 150 tok/s 109 tok/s 68 tok/s | ~1.5s ~1.5s ~1.5s | |
#211 | Mixtral-8x7B-v0.1 | 46.7B (7B active) | INT4 Q8 FP16 | 97 tok/s 67 tok/s 40 tok/s | ~3.1s ~3.1s ~3.1s | |
#212 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 98 tok/s 65 tok/s 37 tok/s | ~3.0s ~3.0s ~3.0s | |
#213 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 212 tok/s 175 tok/s 126 tok/s | ~628 ms ~629 ms ~631 ms | |
#214 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 167 tok/s 125 tok/s 81 tok/s | ~1.2s ~1.2s ~1.2s | |
#215 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 247 tok/s 218 tok/s 174 tok/s | ~340 ms ~340 ms ~341 ms | |
#216 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 150 tok/s 109 tok/s 68 tok/s | ~1.5s ~1.5s ~1.5s | |
#217 | 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 | |
#218 | 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 | |
#219 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 235 tok/s 203 tok/s 157 tok/s | ~431 ms ~431 ms ~433 ms | |
#220 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 194 tok/s 154 tok/s 106 tok/s | ~829 ms ~830 ms ~833 ms | |
#221 | Phi-3-medium | 14B | INT4 Q8 FP16 | 66 tok/s 41 tok/s 22 tok/s | ~5.2s ~5.2s ~5.3s | |
#222 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 81 tok/s 60 tok/s 37 tok/s | ~2.7s ~2.7s ~2.7s | |
#223 | Yi-34B | 34B | INT4 Q8 FP16 | 25 tok/s 16 tok/s 9 tok/s | ~12.5s ~12.5s ~12.6s | |
#224 | Qwen2-7B | 7B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
#225 | Phi-3-small | 7B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~2.7s ~2.7s ~2.7s | |
#226 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 235 tok/s 203 tok/s 157 tok/s | ~431 ms ~431 ms ~433 ms | |
#227 | 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 | |
#228 | Falcon-180B | 180B | INT4 | 7 tok/s | ~65.0s | |
#229 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 81 tok/s 60 tok/s 37 tok/s | ~2.7s ~2.7s ~2.7s | |
#230 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 201 tok/s 159 tok/s 108 tok/s | ~829 ms ~830 ms ~833 ms | |
#231 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 89 tok/s 67 tok/s 42 tok/s | ~2.3s ~2.3s ~2.3s | |
#232 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 89 tok/s 67 tok/s 42 tok/s | ~2.3s ~2.3s ~2.3s | |
#233 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 89 tok/s 67 tok/s 42 tok/s | ~2.3s ~2.3s ~2.3s | |
未上榜模型（按推理速度排序） | ||||||
- | 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 | |
- | 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 | |
- | 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 | |
- | 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 | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 167 tok/s 125 tok/s 81 tok/s | ~1.2s ~1.2s ~1.2s | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 Q8 FP16 | 152 tok/s 117 tok/s 77 tok/s | ~1.5s ~1.5s ~1.5s | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 Q8 FP16 | 152 tok/s 117 tok/s 77 tok/s | ~1.5s ~1.5s ~1.5s | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 Q8 FP16 | 148 tok/s 115 tok/s 76 tok/s | ~1.5s ~1.5s ~1.5s | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 Q8 FP16 | 148 tok/s 115 tok/s 76 tok/s | ~1.5s ~1.5s ~1.5s | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 Q8 FP16 | 147 tok/s 114 tok/s 76 tok/s | ~1.6s ~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 | |
- | 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 Q8 | 123 tok/s 100 tok/s | ~2.1s ~2.1s | |
- | 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 | |
- | 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 | |
- | Laguna S 2.1 | 118B (8B active) | INT4 Q8 | 74 tok/s 51 tok/s | ~4.5s ~4.9s | |
- | 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 | |
- | Hunyuan A13B | 80B (13B active) | INT4 Q8 | 30 tok/s 25 tok/s | ~5.7s ~5.7s | |
- | Falcon-40B | 40B | INT4 Q8 FP16 | 28 tok/s 16 tok/s 8 tok/s | ~14.6s ~14.7s ~14.7s | |
- | Kimi-Dev-72B | 72B | INT4 Q8 | 13 tok/s 8 tok/s | ~26.3s ~26.4s | |
- | Typhoon-2-70B | 70B | INT4 Q8 FP16 | 13 tok/s 8 tok/s 4 tok/s | ~25.6s ~25.6s ~30.2s | |
- | GLM-130B | 130B | INT4 Q8 | 7 tok/s 4 tok/s | ~47.4s ~55.9s | |
推理能力评估
不同量化精度下可运行的最大模型参数级别。
上下文长度:
4位量化
70B+ 模型
8位精度
70B 模型
16位全精度
32B 模型
微调能力评估
本地模型训练与适配器微调支持能力。
微调上下文:
QLoRA
70B+ 模型
LoRA
70B 模型
全参数微调
7B-8B 模型
负载与选型建议
Apple M2 Ultra (192GB) 上的最佳量化精度与运行规格建议。
最佳推理区间
适合在 Q4/Q8 精度下运行 70B 参数级模型并支持 32k 上下文扩展，或对中小型模型进行高并发批处理推理。
显存带宽与推理速率
具备 800 GB/s 聚合带宽，单批次推理处于显存带宽受限模式。8B Q4 模型预估生成速度约 178 tok/s，70B Q4 模型预估生成速度约 21 tok/s。
统一内存配额
采用 75% 可用分配预算建模，以保留系统内存供 macOS 系统及图形渲染进程稳定运行。