Apple M4 Pro (64GB)
The Apple M4 Pro (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 273 GB/s unified memory bandwidth.
Memory
64 GB
Usable Memory Ceiling
48 GB (75% usable budget)
Bandwidth
273 GB/s
Max Inference Class
32B Models (Q4)
TDP
85W
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 M4 Pro (64GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on Apple M4 Pro (64GB).
Sort by:
Context:
KV Cache:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#36 | Qwen 3.8 27B | 27B | INT4 Q8 | 14 tok/s 8 tok/s | ~29.4s ~29.5s | |
#80 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 Q8 | 61 tok/s 42 tok/s | ~5.8s ~5.8s | |
#86 | Qwen3.5-27B | 27B | INT4 Q8 | 14 tok/s 8 tok/s | ~29.4s ~29.5s | |
#93 | Sarvam-30B | 32B (2.4B active) | INT4 Q8 | 81 tok/s 60 tok/s | ~4.0s ~4.0s | |
#99 | Muse Glimmer 30B | 30B | INT4 Q8 | 13 tok/s 7 tok/s | ~32.6s ~32.7s | |
#102 | Phi-4 Reasoning Plus | 14B | INT4 Q8 FP16 | 19 tok/s 13 tok/s 7 tok/s | ~15.5s ~15.5s ~15.6s | |
#103 | Qwen3.6 35B A3B | 35B (3B active) | INT4 Q8 | 72 tok/s 51 tok/s | ~4.7s ~4.7s | |
#105 | MiMo V2 Flash | 15B (309B active) | INT4 Q8 FP16 | 1 tok/s 1 tok/s 1 tok/s | ~321.8s ~322.4s ~323.7s | |
#110 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 Q8 | 66 tok/s 45 tok/s | ~5.3s ~5.3s | |
#117 | Nemotron 3.5 Bolt 74B A9B | 74B | INT4 | 5 tok/s | ~86.7s | |
#120 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 Q8 | 72 tok/s 51 tok/s | ~4.7s ~4.7s | |
#121 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 39 tok/s 23 tok/s 12 tok/s | ~10.0s ~10.0s ~10.1s | |
#127 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 48 tok/s 29 tok/s 15 tok/s | ~7.8s ~7.8s ~7.9s | |
#130 | Gemma 4 12B | 11.95B | INT4 Q8 FP16 | 22 tok/s 15 tok/s 8 tok/s | ~13.2s ~13.3s ~13.3s | |
#136 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 73 tok/s 47 tok/s 26 tok/s | ~4.6s ~4.6s ~4.6s | |
#139 | GPT-OSS 20B | 21B (3.6B active) | INT4 Q8 FP16 | 30 tok/s 26 tok/s 17 tok/s | ~4.9s ~4.9s ~5.8s | |
#140 | GLM-4V | 9B | INT4 Q8 FP16 | 28 tok/s 19 tok/s 11 tok/s | ~10.0s ~10.0s ~10.1s | |
#145 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 12 tok/s 7 tok/s 4 tok/s | ~31.6s ~31.6s ~31.8s | |
#150 | Qwen3-30B-A3B | 30B (3B active) | INT4 Q8 | 73 tok/s 52 tok/s | ~4.6s ~4.6s | |
#152 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 43 tok/s 26 tok/s 14 tok/s | ~8.9s ~8.9s ~9.0s | |
#157 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 43 tok/s 26 tok/s 14 tok/s | ~8.9s ~8.9s ~9.0s | |
#158 | Mistral Large 3 | 41B (675B active) | INT4 | 1 tok/s | ~702.5s | |
#159 | Qwen2.5-72B | 72B | INT4 | 5 tok/s | ~84.4s | |
#161 | GLM-4 | 32B | INT4 Q8 | 9 tok/s 6 tok/s | ~34.8s ~37.8s | |
#162 | DeepSeek-R1 70B | 70B | INT4 | 6 tok/s | ~75.5s | |
#163 | Gemma 3 27B | 27B | INT4 Q8 | 14 tok/s 8 tok/s | ~29.4s ~29.5s | |
#164 | Phi-4 | 14B | INT4 Q8 FP16 | 26 tok/s 15 tok/s 8 tok/s | ~15.5s ~15.5s ~15.5s | |
#165 | Llama 3.3 70B | 70B | INT4 | 6 tok/s | ~75.5s | |
#166 | Qwen3-32B | 32B | INT4 Q8 | 12 tok/s 7 tok/s | ~34.7s ~34.8s | |
#167 | Hunyuan Standard | 52B (389B active) | INT4 | 1 tok/s | ~405.8s | |
#168 | DeepSeek-R1 32B | 32B | INT4 Q8 | 13 tok/s 7 tok/s | ~34.7s ~34.8s | |
#169 | Gemma 4 31B | 30.7B | INT4 Q8 | 13 tok/s 7 tok/s | ~33.3s ~33.4s | |
#171 | Magistral Small | 24B | INT4 Q8 | 12 tok/s 8 tok/s | ~26.2s ~26.3s | |
#172 | Qwen2.5-32B | 32B | INT4 Q8 | 12 tok/s 7 tok/s | ~34.7s ~34.8s | |
#174 | OLMo 3.1 32B Instruct | 32B | INT4 Q8 | 9 tok/s 6 tok/s | ~34.8s ~37.8s | |
#175 | Llama 3.1 70B | 70B | INT4 | 6 tok/s | ~75.5s | |
#176 | DeepSeek-R1 14B | 14B | INT4 Q8 FP16 | 27 tok/s 16 tok/s 8 tok/s | ~15.5s ~15.5s ~15.5s | |
#177 | Ministral 3 14B | 14B | INT4 Q8 FP16 | 19 tok/s 13 tok/s 7 tok/s | ~15.5s ~15.5s ~15.6s | |
#180 | Gemma 3 12B | 12B | INT4 Q8 FP16 | 30 tok/s 18 tok/s 9 tok/s | ~13.3s ~13.3s ~13.4s | |
#183 | Qwen2-72B | 72B | INT4 | 5 tok/s | ~84.4s | |
#184 | Mistral-Small-2501 | 24B | INT4 Q8 FP16 | 16 tok/s 9 tok/s 4 tok/s | ~26.2s ~26.3s ~31.0s | |
#185 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 30 tok/s 21 tok/s 12 tok/s | ~8.9s ~8.9s ~9.0s | |
#186 | Gemma 2 27B | 27B | INT4 Q8 | 14 tok/s 8 tok/s | ~29.4s ~29.5s | |
#187 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 34 tok/s 23 tok/s 14 tok/s | ~7.8s ~7.9s ~7.9s | |
#188 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 114 tok/s 79 tok/s 47 tok/s | ~2.4s ~2.4s ~2.4s | |
#189 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 114 tok/s 79 tok/s 47 tok/s | ~2.4s ~2.4s ~2.4s | |
#190 | Qwen2.5-14B | 14B | INT4 Q8 FP16 | 26 tok/s 15 tok/s 8 tok/s | ~15.5s ~15.5s ~15.5s | |
#191 | OLMo 3.1 32B Think | 32B | INT4 Q8 | 9 tok/s 6 tok/s | ~34.8s ~37.8s | |
#192 | Llama 3 70B | 70B | INT4 | 6 tok/s | ~75.5s | |
#193 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 61 tok/s 38 tok/s 21 tok/s | ~5.8s ~5.8s ~5.8s | |
#195 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 58 tok/s 44 tok/s 28 tok/s | ~3.5s ~3.5s ~3.5s | |
#196 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 44 tok/s 26 tok/s 14 tok/s | ~8.9s ~8.9s ~9.0s | |
#198 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 39 tok/s 23 tok/s 12 tok/s | ~10.0s ~10.0s ~10.1s | |
#199 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 Q8 | 73 tok/s 52 tok/s | ~4.6s ~4.6s | |
#200 | Kimi Linear 48B A3B Instruct | 48B (3B active) | INT4 | 23 tok/s | ~5.0s | |
#201 | Qwen3-4B | 4B | INT4 Q8 FP16 | 73 tok/s 47 tok/s 26 tok/s | ~4.6s ~4.6s ~4.6s | |
#202 | Qwen3-14B | 14B | INT4 Q8 FP16 | 26 tok/s 15 tok/s 8 tok/s | ~15.5s ~15.5s ~15.5s | |
#203 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 73 tok/s 47 tok/s 26 tok/s | ~4.6s ~4.6s ~4.6s | |
#204 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 49 tok/s 29 tok/s 16 tok/s | ~7.8s ~7.8s ~7.9s | |
#205 | OLMo 3 32B Base | 32B | INT4 Q8 | 9 tok/s 6 tok/s | ~34.8s ~37.8s | |
#206 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 182 tok/s 142 tok/s 95 tok/s | ~987 ms ~988 ms ~992 ms | |
#207 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 43 tok/s 26 tok/s 14 tok/s | ~8.9s ~8.9s ~9.0s | |
#207 | Qwen3-8B | 8B | INT4 Q8 FP16 | 43 tok/s 26 tok/s 14 tok/s | ~8.9s ~8.9s ~9.0s | |
#210 | Nemotron 3.5 Lightning | 30B (3B active) | INT4 Q8 | 27 tok/s 25 tok/s | ~4.6s ~4.6s | |
#211 | Command R | 35B | INT4 Q8 | 9 tok/s 5 tok/s | ~37.9s ~41.3s | |
#212 | Llama 3 8B | 8B | INT4 Q8 FP16 | 43 tok/s 26 tok/s 14 tok/s | ~8.9s ~8.9s ~9.0s | |
#213 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 125 tok/s 89 tok/s 54 tok/s | ~2.1s ~2.1s ~2.1s | |
#214 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 219 tok/s 198 tok/s 161 tok/s | ~325 ms ~325 ms ~326 ms | |
#216 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 203 tok/s 164 tok/s 115 tok/s | ~729 ms ~730 ms ~733 ms | |
#217 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 76 tok/s 49 tok/s 27 tok/s | ~4.4s ~4.4s ~4.4s | |
#218 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 48 tok/s 29 tok/s 15 tok/s | ~7.8s ~7.8s ~7.9s | |
#219 | Mixtral-8x7B-v0.1 | 46.7B (7B active) | INT4 Q8 | 42 tok/s 24 tok/s | ~9.1s ~10.7s | |
#220 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 43 tok/s 26 tok/s 14 tok/s | ~8.9s ~8.9s ~9.0s | |
#221 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 135 tok/s 97 tok/s 60 tok/s | ~1.8s ~1.8s ~1.8s | |
#222 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 89 tok/s 59 tok/s 33 tok/s | ~3.5s ~3.5s ~3.5s | |
#223 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 76 tok/s 49 tok/s 27 tok/s | ~4.4s ~4.4s ~4.4s | |
#224 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 58 tok/s 49 tok/s 34 tok/s | ~2.6s ~2.6s ~2.6s | |
#225 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 114 tok/s 79 tok/s 47 tok/s | ~2.4s ~2.4s ~2.4s | |
#226 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 46 tok/s 28 tok/s 15 tok/s | ~8.2s ~8.2s ~8.2s | |
#227 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 164 tok/s 124 tok/s 81 tok/s | ~1.3s ~1.3s ~1.3s | |
#228 | Phi-3-medium | 14B | INT4 Q8 FP16 | 26 tok/s 15 tok/s 8 tok/s | ~15.5s ~15.5s ~15.5s | |
#229 | Yi-34B | 34B | INT4 Q8 | 9 tok/s 5 tok/s | ~36.9s ~40.1s | |
#230 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 34 tok/s 23 tok/s 14 tok/s | ~7.8s ~7.9s ~7.9s | |
#231 | Qwen2-7B | 7B | INT4 Q8 FP16 | 48 tok/s 29 tok/s 15 tok/s | ~7.8s ~7.8s ~7.9s | |
#232 | Phi-3-small | 7B | INT4 Q8 FP16 | 48 tok/s 29 tok/s 15 tok/s | ~7.8s ~7.8s ~7.9s | |
#233 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 46 tok/s 28 tok/s 15 tok/s | ~8.2s ~8.2s ~8.2s | |
#234 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 164 tok/s 124 tok/s 81 tok/s | ~1.3s ~1.3s ~1.3s | |
#236 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 34 tok/s 23 tok/s 14 tok/s | ~7.8s ~7.9s ~7.9s | |
#237 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 122 tok/s 83 tok/s 48 tok/s | ~2.4s ~2.4s ~2.4s | |
#238 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 38 tok/s 27 tok/s 16 tok/s | ~6.8s ~6.8s ~6.8s | |
#239 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 38 tok/s 27 tok/s 16 tok/s | ~6.8s ~6.8s ~6.8s | |
#240 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 38 tok/s 27 tok/s 16 tok/s | ~6.8s ~6.8s ~6.8s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 244 tok/s 214 tok/s 167 tok/s | ~361 ms ~362 ms ~363 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 215 tok/s 178 tok/s 129 tok/s | ~604 ms ~605 ms ~607 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 215 tok/s 178 tok/s 129 tok/s | ~604 ms ~605 ms ~607 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 211 tok/s 189 tok/s 152 tok/s | ~362 ms ~362 ms ~364 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 211 tok/s 189 tok/s 152 tok/s | ~362 ms ~362 ms ~364 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 203 tok/s 164 tok/s 115 tok/s | ~729 ms ~730 ms ~733 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 174 tok/s 130 tok/s 83 tok/s | ~1.3s ~1.3s ~1.3s | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 164 tok/s 124 tok/s 81 tok/s | ~1.3s ~1.3s ~1.3s | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 164 tok/s 124 tok/s 81 tok/s | ~1.3s ~1.3s ~1.3s | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 135 tok/s 97 tok/s 60 tok/s | ~1.8s ~1.8s ~1.8s | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 135 tok/s 97 tok/s 60 tok/s | ~1.8s ~1.8s ~1.8s | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 125 tok/s 89 tok/s 54 tok/s | ~2.1s ~2.1s ~2.1s | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 122 tok/s 85 tok/s 51 tok/s | ~2.2s ~2.2s ~2.2s | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 95 tok/s 61 tok/s 34 tok/s | ~3.5s ~3.5s ~3.5s | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 93 tok/s 77 tok/s 54 tok/s | ~1.6s ~1.6s ~1.6s | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 93 tok/s 77 tok/s 54 tok/s | ~1.6s ~1.6s ~1.6s | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 93 tok/s 77 tok/s 54 tok/s | ~1.6s ~1.6s ~1.6s | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 91 tok/s 59 tok/s 34 tok/s | ~3.5s ~3.5s ~3.5s | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 FP16 | 91 tok/s 63 tok/s 38 tok/s | ~3.4s ~3.4s ~3.4s | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 89 tok/s 59 tok/s 33 tok/s | ~3.5s ~3.5s ~3.5s | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 89 tok/s 59 tok/s 33 tok/s | ~3.5s ~3.5s ~3.5s | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 89 tok/s 59 tok/s 33 tok/s | ~3.5s ~3.5s ~3.5s | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 89 tok/s 59 tok/s 33 tok/s | ~3.5s ~3.5s ~3.5s | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 89 tok/s 59 tok/s 33 tok/s | ~3.5s ~3.5s ~3.5s | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 89 tok/s 59 tok/s 33 tok/s | ~3.5s ~3.5s ~3.5s | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 Q8 FP16 | 83 tok/s 60 tok/s 33 tok/s | ~3.9s ~3.9s ~4.6s | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 Q8 FP16 | 77 tok/s 54 tok/s 30 tok/s | ~4.3s ~4.3s ~4.7s | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 Q8 FP16 | 77 tok/s 54 tok/s 30 tok/s | ~4.3s ~4.3s ~4.7s | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 Q8 | 74 tok/s 52 tok/s | ~4.5s ~4.5s | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 Q8 | 74 tok/s 52 tok/s | ~4.5s ~4.5s | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 73 tok/s 47 tok/s 26 tok/s | ~4.6s ~4.6s ~4.6s | |
- | Hy-Memory 30B A3B | 30B (3B active) | INT4 Q8 | 73 tok/s 52 tok/s | ~4.6s ~4.6s | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 Q8 | 73 tok/s 52 tok/s | ~4.6s ~4.6s | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 73 tok/s 47 tok/s 26 tok/s | ~4.6s ~4.6s ~4.6s | |
- | MiniCPM-V 4.7 35B A3B | 35B (3B active) | INT4 Q8 | 72 tok/s 51 tok/s | ~4.7s ~4.7s | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 70 tok/s 56 tok/s 38 tok/s | ~2.4s ~2.4s ~2.5s | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 61 tok/s 47 tok/s 31 tok/s | ~3.2s ~3.2s ~3.2s | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 58 tok/s 44 tok/s 28 tok/s | ~3.5s ~3.5s ~3.5s | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 58 tok/s 44 tok/s 28 tok/s | ~3.5s ~3.5s ~3.5s | |
- | AliceAI Foundation 80B A3B Base | 80B (3B active) | INT4 | 54 tok/s | ~6.8s | |
- | Kolibri 1 | 78B (3.5B active) | INT4 | 51 tok/s | ~7.3s | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 50 tok/s 30 tok/s 16 tok/s | ~7.8s ~7.8s ~7.9s | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 48 tok/s 29 tok/s 15 tok/s | ~7.8s ~7.8s ~7.9s | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 48 tok/s 29 tok/s 15 tok/s | ~7.8s ~7.8s ~7.9s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 46 tok/s 28 tok/s 15 tok/s | ~8.2s ~8.2s ~8.2s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 FP16 | 44 tok/s 26 tok/s 14 tok/s | ~8.9s ~8.9s ~9.0s | |
- | LensVLM 9B | 9B | INT4 Q8 FP16 | 39 tok/s 23 tok/s 12 tok/s | ~10.0s ~10.0s ~10.1s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 FP16 | 39 tok/s 23 tok/s 12 tok/s | ~10.0s ~10.0s ~10.1s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 38 tok/s 27 tok/s 16 tok/s | ~6.8s ~6.8s ~6.8s | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 38 tok/s 27 tok/s 16 tok/s | ~6.8s ~6.8s ~6.8s | |
- | Falcon3-10B | 10B | INT4 Q8 FP16 | 35 tok/s 21 tok/s 11 tok/s | ~11.1s ~11.1s ~11.2s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 Q8 FP16 | 35 tok/s 31 tok/s 22 tok/s | ~4.1s ~4.1s ~4.1s | |
- | Falcon2-11B | 11B | INT4 Q8 FP16 | 34 tok/s 20 tok/s 10 tok/s | ~12.2s ~12.2s ~12.2s | |
- | Hunyuan Lite | 7B | INT4 Q8 FP16 | 34 tok/s 23 tok/s 14 tok/s | ~7.8s ~7.9s ~7.9s | |
- | OLMo 3 7B Base | 7B | INT4 Q8 FP16 | 34 tok/s 23 tok/s 14 tok/s | ~7.8s ~7.9s ~7.9s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 FP16 | 33 tok/s 23 tok/s 14 tok/s | ~7.9s ~8.0s ~8.0s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 FP16 | 33 tok/s 23 tok/s 14 tok/s | ~7.9s ~8.0s ~8.0s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 FP16 | 30 tok/s 21 tok/s 12 tok/s | ~8.9s ~8.9s ~9.0s | |
- | Typhoon-2-8B | 8B | INT4 Q8 FP16 | 30 tok/s 21 tok/s 12 tok/s | ~8.9s ~8.9s ~9.0s | |
- | GLM-4-9B | 9B | INT4 Q8 FP16 | 28 tok/s 19 tok/s 11 tok/s | ~10.0s ~10.0s ~10.1s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 FP16 | 28 tok/s 19 tok/s 11 tok/s | ~10.0s ~10.0s ~10.1s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 FP16 | 28 tok/s 19 tok/s 11 tok/s | ~10.0s ~10.0s ~10.1s | |
- | Yi-9B | 9B | INT4 Q8 FP16 | 28 tok/s 19 tok/s 11 tok/s | ~10.0s ~10.0s ~10.1s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 FP16 | 27 tok/s 19 tok/s 11 tok/s | ~10.2s ~10.3s ~10.3s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 FP16 | 27 tok/s 19 tok/s 11 tok/s | ~10.2s ~10.3s ~10.3s | |
- | GreenMind-14B-R1 | 14B | INT4 Q8 FP16 | 19 tok/s 13 tok/s 7 tok/s | ~15.5s ~15.5s ~15.6s | |
- | AREX-2 | 27B | INT4 Q8 | 14 tok/s 8 tok/s | ~29.4s ~29.5s | |
- | PPLX Decider v1 27B | 27B | INT4 Q8 | 14 tok/s 8 tok/s | ~29.4s ~29.5s | |
- | PPLX Decider v1.1 27B | 27B | INT4 Q8 | 14 tok/s 8 tok/s | ~29.4s ~29.5s | |
- | Agnes 3.0 Flash | 33B | INT4 Q8 | 12 tok/s 7 tok/s | ~35.8s ~35.8s | |
- | Falcon-40B | 40B | INT4 Q8 | 10 tok/s 5 tok/s | ~43.2s ~47.1s | |
- | Kimi-Dev-72B | 72B | INT4 | 4 tok/s | ~91.4s | |
- | Typhoon-2-70B | 70B | INT4 | 4 tok/s | ~88.8s | |
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 M4 Pro (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 273 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 61 tok/s on an 8B Q4 model and 7 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