NVIDIA RTX A5000 (24GB)
The NVIDIA RTX A5000 (24GB) features 24 GB of dedicated VRAM and 768 GB/s memory bandwidth, supporting CUDA and TensorRT-LLM runtimes for full-precision and quantized inference.
Memory
24 GB
Usable Memory Ceiling
24 GB
Bandwidth
768 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 NVIDIA RTX A5000 (24GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA RTX A5000 (24GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#48 | Qwen 3.8 27B | 27B | INT4 | 38 tok/s | ~2.7s | |
#83 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 | 130 tok/s | ~569 ms | |
#93 | Qwen3.5-27B | 27B | INT4 | 38 tok/s | ~2.7s | |
#105 | Sarvam-30B | 32B (2.4B active) | INT4 | 169 tok/s | ~367 ms | |
#106 | Qwen3.6 35B A3B | 35B (3B active) | INT4 | 147 tok/s | ~464 ms | |
#110 | Muse Glimmer 30B | 30B | INT4 | 35 tok/s | ~2.9s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 Q8 | 4 tok/s 2 tok/s | ~29.0s ~31.7s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 Q8 | 49 tok/s 34 tok/s | ~1.4s ~1.4s | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 145 tok/s | ~480 ms | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 93 tok/s 59 tok/s 31 tok/s | ~908 ms ~915 ms ~1.0s | |
#126 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 | 147 tok/s | ~464 ms | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 111 tok/s 72 tok/s 41 tok/s | ~712 ms ~717 ms ~728 ms | |
#135 | Gemma 4 12B | 11.95B | INT4 Q8 | 56 tok/s 39 tok/s | ~1.2s ~1.2s | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 157 tok/s 109 tok/s 65 tok/s | ~420 ms ~423 ms ~429 ms | |
#143 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 76 tok/s | ~456 ms | |
#144 | GLM-4V | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 28 tok/s | ~912 ms ~918 ms ~1.0s | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 33 tok/s 20 tok/s 10 tok/s | ~2.9s ~2.9s ~2.9s | |
#153 | Qwen3-30B-A3B | 30B (3B active) | INT4 | 157 tok/s | ~419 ms | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 102 tok/s 65 tok/s 36 tok/s | ~809 ms ~815 ms ~827 ms | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 102 tok/s 65 tok/s 36 tok/s | ~809 ms ~815 ms ~827 ms | |
#165 | GLM-4 | 32B | INT4 | 23 tok/s | ~3.7s | |
#166 | Phi-4 | 14B | INT4 Q8 | 66 tok/s 40 tok/s | ~1.4s ~1.4s | |
#167 | Gemma 3 27B | 27B | INT4 | 38 tok/s | ~2.7s | |
#170 | DeepSeek-R1 32B | 32B | INT4 | 34 tok/s | ~3.1s | |
#171 | Qwen3-32B | 32B | INT4 | 33 tok/s | ~3.1s | |
#175 | Magistral Small | 24B | INT4 | 32 tok/s | ~2.4s | |
#176 | OLMo 3.1 32B Instruct | 32B | INT4 | 23 tok/s | ~3.7s | |
#177 | Qwen2.5-32B | 32B | INT4 | 33 tok/s | ~3.1s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 83 tok/s 60 tok/s 36 tok/s | ~715 ms ~720 ms ~731 ms | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 68 tok/s 41 tok/s | ~1.4s ~1.4s | |
#183 | Ministral 3 14B | 14B | INT4 Q8 | 49 tok/s 34 tok/s | ~1.4s ~1.4s | |
#186 | Gemma 3 12B | 12B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 22 tok/s | ~1.2s ~1.2s ~1.4s | |
#188 | Mistral-Small-2501 | 24B | INT4 | 42 tok/s | ~2.4s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 76 tok/s 54 tok/s 31 tok/s | ~813 ms ~818 ms ~901 ms | |
#190 | Gemma 4 31B | 30.7B | INT4 | 34 tok/s | ~3.0s | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~226 ms ~227 ms ~230 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~226 ms ~227 ms ~230 ms | |
#193 | Gemma 2 27B | 27B | INT4 | 38 tok/s | ~2.7s | |
#194 | Qwen2.5-14B | 14B | INT4 Q8 | 66 tok/s 40 tok/s | ~1.4s ~1.4s | |
#195 | OLMo 3.1 32B Think | 32B | INT4 | 23 tok/s | ~3.7s | |
#196 | Nemotron 3.5 Lightning | 30B (3B active) | INT4 | 65 tok/s | ~464 ms | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 136 tok/s 92 tok/s 54 tok/s | ~527 ms ~531 ms ~538 ms | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 104 tok/s 66 tok/s 36 tok/s | ~809 ms ~815 ms ~827 ms | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 157 tok/s 109 tok/s 65 tok/s | ~420 ms ~423 ms ~429 ms | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 131 tok/s 105 tok/s 71 tok/s | ~325 ms ~327 ms ~331 ms | |
#206 | OLMo 3 32B Base | 32B | INT4 | 23 tok/s | ~3.7s | |
#207 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 93 tok/s 59 tok/s 31 tok/s | ~908 ms ~915 ms ~1.0s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 287 tok/s 248 tok/s 190 tok/s | ~96 ms ~96 ms ~98 ms | |
#209 | Qwen3-14B | 14B | INT4 Q8 | 66 tok/s 40 tok/s | ~1.4s ~1.4s | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 157 tok/s 109 tok/s 65 tok/s | ~420 ms ~423 ms ~429 ms | |
#211 | Qwen3-8B | 8B | INT4 Q8 FP16 | 102 tok/s 65 tok/s 36 tok/s | ~809 ms ~815 ms ~827 ms | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 114 tok/s 73 tok/s 41 tok/s | ~712 ms ~717 ms ~728 ms | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 229 tok/s 181 tok/s 123 tok/s | ~194 ms ~195 ms ~198 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 102 tok/s 65 tok/s 36 tok/s | ~809 ms ~815 ms ~827 ms | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 317 tok/s 301 tok/s 268 tok/s | ~36 ms ~36 ms ~37 ms | |
#217 | Command R | 35B | INT4 | 22 tok/s | ~4.0s | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 305 tok/s 271 tok/s 217 tok/s | ~73 ms ~73 ms ~74 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 FP16 | 102 tok/s 65 tok/s 36 tok/s | ~809 ms ~815 ms ~827 ms | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 161 tok/s 113 tok/s 68 tok/s | ~400 ms ~403 ms ~409 ms | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 111 tok/s 72 tok/s 41 tok/s | ~712 ms ~717 ms ~728 ms | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 102 tok/s 65 tok/s 36 tok/s | ~809 ms ~815 ms ~827 ms | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 240 tok/s 192 tok/s 133 tok/s | ~173 ms ~174 ms ~176 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 182 tok/s 132 tok/s 82 tok/s | ~323 ms ~325 ms ~329 ms | |
#227 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 | 157 tok/s | ~419 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 161 tok/s 113 tok/s 68 tok/s | ~400 ms ~403 ms ~409 ms | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 131 tok/s 114 tok/s 84 tok/s | ~244 ms ~245 ms ~248 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 108 tok/s 70 tok/s 39 tok/s | ~741 ms ~746 ms ~757 ms | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 270 tok/s 228 tok/s 169 tok/s | ~120 ms ~121 ms ~122 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~226 ms ~227 ms ~230 ms | |
#233 | Phi-3-medium | 14B | INT4 Q8 | 66 tok/s 40 tok/s | ~1.4s ~1.4s | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 83 tok/s 60 tok/s 36 tok/s | ~715 ms ~720 ms ~731 ms | |
#235 | Yi-34B | 34B | INT4 | 22 tok/s | ~3.9s | |
#236 | Qwen2-7B | 7B | INT4 Q8 FP16 | 111 tok/s 72 tok/s 41 tok/s | ~712 ms ~717 ms ~728 ms | |
#237 | Phi-3-small | 7B | INT4 Q8 FP16 | 111 tok/s 72 tok/s 41 tok/s | ~712 ms ~717 ms ~728 ms | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 270 tok/s 228 tok/s 169 tok/s | ~120 ms ~121 ms ~122 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 108 tok/s 70 tok/s 39 tok/s | ~741 ms ~746 ms ~757 ms | |
#241 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 83 tok/s 60 tok/s 36 tok/s | ~715 ms ~720 ms ~731 ms | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 226 tok/s 172 tok/s 112 tok/s | ~226 ms ~227 ms ~230 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 91 tok/s 67 tok/s 41 tok/s | ~618 ms ~622 ms ~631 ms | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 91 tok/s 67 tok/s 41 tok/s | ~618 ms ~622 ms ~631 ms | |
#245 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 91 tok/s 67 tok/s 41 tok/s | ~618 ms ~622 ms ~631 ms | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 335 tok/s 313 tok/s 274 tok/s | ~39 ms ~40 ms ~40 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 315 tok/s 284 tok/s 233 tok/s | ~61 ms ~62 ms ~62 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 315 tok/s 284 tok/s 233 tok/s | ~61 ms ~62 ms ~62 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 311 tok/s 294 tok/s 259 tok/s | ~40 ms ~40 ms ~40 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 311 tok/s 294 tok/s 259 tok/s | ~40 ms ~40 ms ~40 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 305 tok/s 271 tok/s 217 tok/s | ~73 ms ~73 ms ~74 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 304 tok/s 270 tok/s 215 tok/s | ~74 ms ~74 ms ~75 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 304 tok/s 270 tok/s 215 tok/s | ~74 ms ~74 ms ~75 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 302 tok/s 267 tok/s 212 tok/s | ~76 ms ~77 ms ~78 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 282 tok/s 242 tok/s 183 tok/s | ~103 ms ~103 ms ~105 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 282 tok/s 242 tok/s 183 tok/s | ~103 ms ~103 ms ~105 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 282 tok/s 242 tok/s 183 tok/s | ~103 ms ~103 ms ~105 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 280 tok/s 234 tok/s 172 tok/s | ~120 ms ~121 ms ~122 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 270 tok/s 228 tok/s 169 tok/s | ~120 ms ~121 ms ~122 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 270 tok/s 228 tok/s 169 tok/s | ~120 ms ~121 ms ~122 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 256 tok/s 211 tok/s 151 tok/s | ~143 ms ~144 ms ~146 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 251 tok/s 205 tok/s 146 tok/s | ~151 ms ~152 ms ~154 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 240 tok/s 192 tok/s 133 tok/s | ~173 ms ~174 ms ~176 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 240 tok/s 192 tok/s 133 tok/s | ~173 ms ~174 ms ~176 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 240 tok/s 192 tok/s 133 tok/s | ~173 ms ~174 ms ~176 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 240 tok/s 192 tok/s 133 tok/s | ~173 ms ~174 ms ~176 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 229 tok/s 181 tok/s 123 tok/s | ~194 ms ~195 ms ~198 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 229 tok/s 181 tok/s 123 tok/s | ~194 ms ~195 ms ~198 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 229 tok/s 181 tok/s 123 tok/s | ~194 ms ~195 ms ~198 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 225 tok/s 176 tok/s 118 tok/s | ~204 ms ~205 ms ~208 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 FP16 | 216 tok/s 166 tok/s 105 tok/s | ~254 ms ~255 ms ~280 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~226 ms ~227 ms ~230 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~226 ms ~227 ms ~230 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~226 ms ~227 ms ~230 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~226 ms ~227 ms ~230 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~226 ms ~227 ms ~230 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~226 ms ~227 ms ~230 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 215 tok/s 166 tok/s 110 tok/s | ~226 ms ~227 ms ~230 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 106 tok/s | ~236 ms ~237 ms ~240 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 208 tok/s 158 tok/s 103 tok/s | ~245 ms ~247 ms ~250 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 204 tok/s 154 tok/s 100 tok/s | ~256 ms ~257 ms ~261 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 197 tok/s 147 tok/s 94 tok/s | ~274 ms ~276 ms ~280 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 195 tok/s 145 tok/s 92 tok/s | ~280 ms ~282 ms ~286 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 195 tok/s 145 tok/s 92 tok/s | ~280 ms ~282 ms ~286 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 190 tok/s 136 tok/s 84 tok/s | ~322 ms ~324 ms ~329 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 187 tok/s 163 tok/s 123 tok/s | ~152 ms ~153 ms ~155 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 187 tok/s 163 tok/s 123 tok/s | ~152 ms ~153 ms ~155 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 187 tok/s 163 tok/s 123 tok/s | ~152 ms ~153 ms ~155 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 184 tok/s 133 tok/s 82 tok/s | ~322 ms ~325 ms ~329 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 FP16 | 184 tok/s 140 tok/s 82 tok/s | ~315 ms ~317 ms ~375 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 182 tok/s 132 tok/s 82 tok/s | ~323 ms ~325 ms ~329 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 182 tok/s 132 tok/s 82 tok/s | ~323 ms ~325 ms ~329 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 182 tok/s 132 tok/s 82 tok/s | ~323 ms ~325 ms ~329 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 182 tok/s 132 tok/s 82 tok/s | ~323 ms ~325 ms ~329 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 182 tok/s 132 tok/s 82 tok/s | ~323 ms ~325 ms ~329 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 182 tok/s 132 tok/s 82 tok/s | ~323 ms ~325 ms ~329 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 172 tok/s | ~356 ms | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 Q8 | 163 tok/s 110 tok/s | ~393 ms ~463 ms | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 Q8 | 163 tok/s 110 tok/s | ~393 ms ~463 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 158 tok/s | ~413 ms | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 158 tok/s | ~413 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 157 tok/s 109 tok/s 65 tok/s | ~420 ms ~423 ms ~429 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 157 tok/s 109 tok/s 65 tok/s | ~420 ms ~423 ms ~429 ms | |
- | Hy-Memory 30B A3B | 30B (3B active) | INT4 | 157 tok/s | ~419 ms | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 | 157 tok/s | ~419 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 157 tok/s 109 tok/s 65 tok/s | ~420 ms ~423 ms ~429 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 157 tok/s 109 tok/s 65 tok/s | ~420 ms ~423 ms ~429 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 152 tok/s 128 tok/s 92 tok/s | ~228 ms ~229 ms ~232 ms | |
- | MiniCPM-V 4.7 35B A3B | 35B (3B active) | INT4 | 147 tok/s | ~464 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 138 tok/s 93 tok/s 54 tok/s | ~517 ms ~521 ms ~528 ms | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 138 tok/s 93 tok/s 54 tok/s | ~517 ms ~521 ms ~528 ms | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 138 tok/s 93 tok/s 54 tok/s | ~517 ms ~521 ms ~528 ms | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 136 tok/s 111 tok/s 76 tok/s | ~296 ms ~297 ms ~301 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 131 tok/s 105 tok/s 71 tok/s | ~325 ms ~327 ms ~331 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 131 tok/s 105 tok/s 71 tok/s | ~325 ms ~327 ms ~331 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 116 tok/s 74 tok/s 41 tok/s | ~712 ms ~717 ms ~727 ms | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 114 tok/s 74 tok/s 42 tok/s | ~693 ms ~697 ms ~708 ms | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 114 tok/s 74 tok/s 42 tok/s | ~693 ms ~697 ms ~708 ms | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 111 tok/s 72 tok/s 41 tok/s | ~712 ms ~717 ms ~728 ms | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 111 tok/s 72 tok/s 41 tok/s | ~712 ms ~717 ms ~728 ms | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 108 tok/s 70 tok/s 39 tok/s | ~741 ms ~746 ms ~757 ms | |
- | Youtu Parsing Omni | 8B | INT4 Q8 FP16 | 104 tok/s 66 tok/s 36 tok/s | ~809 ms ~815 ms ~827 ms | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 FP16 | 101 tok/s 64 tok/s 36 tok/s | ~819 ms ~825 ms ~837 ms | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 FP16 | 101 tok/s 64 tok/s 36 tok/s | ~819 ms ~825 ms ~837 ms | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 FP16 | 93 tok/s 59 tok/s 31 tok/s | ~908 ms ~915 ms ~1.0s | |
- | LensVLM 9B | 9B | INT4 Q8 FP16 | 93 tok/s 59 tok/s 31 tok/s | ~908 ms ~915 ms ~1.0s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 FP16 | 93 tok/s 59 tok/s 31 tok/s | ~908 ms ~915 ms ~1.0s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 91 tok/s 67 tok/s 41 tok/s | ~618 ms ~622 ms ~631 ms | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 91 tok/s 67 tok/s 41 tok/s | ~618 ms ~622 ms ~631 ms | |
- | Falcon3-10B | 10B | INT4 Q8 FP16 | 86 tok/s 54 tok/s 28 tok/s | ~1.0s ~1.0s ~1.1s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 Q8 | 86 tok/s 72 tok/s | ~383 ms ~417 ms | |
- | Mochi 1 Preview | 10B | INT4 Q8 FP16 | 86 tok/s 54 tok/s 28 tok/s | ~1.0s ~1.0s ~1.1s | |
- | Falcon2-11B | 11B | INT4 Q8 FP16 | 83 tok/s 51 tok/s 25 tok/s | ~1.1s ~1.1s ~1.3s | |
- | Hunyuan Lite | 7B | INT4 Q8 FP16 | 83 tok/s 60 tok/s 36 tok/s | ~715 ms ~720 ms ~731 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 FP16 | 83 tok/s 60 tok/s 36 tok/s | ~715 ms ~720 ms ~731 ms | |
- | SEA-LION-7B | 7.1B | INT4 Q8 FP16 | 82 tok/s 59 tok/s 36 tok/s | ~725 ms ~730 ms ~740 ms | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 FP16 | 82 tok/s 59 tok/s 36 tok/s | ~725 ms ~730 ms ~740 ms | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 FP16 | 76 tok/s 54 tok/s 31 tok/s | ~813 ms ~818 ms ~901 ms | |
- | Typhoon-2-8B | 8B | INT4 Q8 FP16 | 76 tok/s 54 tok/s 31 tok/s | ~813 ms ~818 ms ~901 ms | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 23 tok/s | ~1.2s ~1.2s ~1.4s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 23 tok/s | ~1.2s ~1.2s ~1.4s | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 23 tok/s | ~1.2s ~1.2s ~1.4s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 23 tok/s | ~1.2s ~1.2s ~1.4s | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 23 tok/s | ~1.2s ~1.2s ~1.4s | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 70 tok/s 43 tok/s | ~1.3s ~1.3s | |
- | GLM-4-9B | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 28 tok/s | ~912 ms ~918 ms ~1.0s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 28 tok/s | ~912 ms ~918 ms ~1.0s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 28 tok/s | ~912 ms ~918 ms ~1.0s | |
- | Yi-9B | 9B | INT4 Q8 FP16 | 69 tok/s 49 tok/s 28 tok/s | ~912 ms ~918 ms ~1.0s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 FP16 | 68 tok/s 48 tok/s 27 tok/s | ~931 ms ~937 ms ~1.0s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 FP16 | 68 tok/s 48 tok/s 27 tok/s | ~931 ms ~937 ms ~1.0s | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 66 tok/s 40 tok/s | ~1.4s ~1.4s | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 66 tok/s 40 tok/s | ~1.4s ~1.4s | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 66 tok/s 40 tok/s | ~1.4s ~1.4s | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 63 tok/s 38 tok/s | ~1.5s ~1.5s | |
- | GreenMind-14B-R1 | 14B | INT4 Q8 | 49 tok/s 34 tok/s | ~1.4s ~1.4s | |
- | Arete 27B | 27B | INT4 | 38 tok/s | ~2.7s | |
- | AREX-2 | 27B | INT4 | 38 tok/s | ~2.7s | |
- | PPLX Decider v1 27B | 27B | INT4 | 38 tok/s | ~2.7s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 38 tok/s | ~2.7s | |
- | Agnes 3.0 Flash | 33B | INT4 | 32 tok/s | ~3.2s | |
- | Falcon-40B | 40B | INT4 | 26 tok/s | ~4.2s | |
Inference Capacity
Maximum model parameter class runnable by weight precision.
Context:
4-bit
32B Models
8-bit
14B Models
16-bit
8B Models
Fine-Tuning Capacity
Hardware capacity for local training and adapter fine-tuning.
Context Length:
QLoRA
32B Models
LoRA
14B Models
Full Parameter Training
3B Models
Workload Recommendations
Guidance for optimal precision and operational ceilings on NVIDIA RTX A5000 (24GB).
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 768 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 171 tok/s on an 8B Q4 model and 20 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning