NVIDIA RTX PRO 4000 Blackwell (24GB)
The NVIDIA RTX PRO 4000 Blackwell (24GB) features 24 GB of dedicated VRAM and 672 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
672 GB/s
Max Inference Class
32B Models (Q4)
TDP
145W
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 PRO 4000 Blackwell (24GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA RTX PRO 4000 Blackwell (24GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#49 | Qwen 3.8 27B | 27B | INT4 | 34 tok/s | ~1.9s | |
#84 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 | 119 tok/s | ~400 ms | |
#94 | Qwen3.5-27B | 27B | INT4 | 34 tok/s | ~1.9s | |
#105 | Sarvam-30B | 32B (2.4B active) | INT4 | 157 tok/s | ~259 ms | |
#107 | Qwen3.6 35B A3B | 35B (3B active) | INT4 | 136 tok/s | ~327 ms | |
#109 | Muse Glimmer 30B | 30B | INT4 | 31 tok/s | ~2.1s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 Q8 | 3 tok/s 2 tok/s | ~20.3s ~22.3s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 Q8 | 44 tok/s 30 tok/s | ~987 ms ~998 ms | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 133 tok/s | ~338 ms | |
#124 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 84 tok/s 53 tok/s 27 tok/s | ~638 ms ~645 ms ~716 ms | |
#127 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 | 136 tok/s | ~327 ms | |
#129 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 101 tok/s 65 tok/s 36 tok/s | ~501 ms ~506 ms ~519 ms | |
#136 | Gemma 4 12B | 11.95B | INT4 Q8 | 50 tok/s 34 tok/s | ~846 ms ~855 ms | |
#141 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~296 ms ~299 ms ~306 ms | |
#144 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 68 tok/s | ~324 ms | |
#146 | GLM-4V | 9B | INT4 Q8 FP16 | 62 tok/s 44 tok/s 25 tok/s | ~642 ms ~649 ms ~721 ms | |
#151 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 29 tok/s 17 tok/s 9 tok/s | ~2.0s ~2.0s ~2.1s | |
#154 | Qwen3-30B-A3B | 30B (3B active) | INT4 | 145 tok/s | ~296 ms | |
#159 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 92 tok/s 58 tok/s 32 tok/s | ~569 ms ~575 ms ~589 ms | |
#160 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 92 tok/s 58 tok/s 32 tok/s | ~569 ms ~575 ms ~589 ms | |
#166 | GLM-4 | 32B | INT4 | 20 tok/s | ~2.6s | |
#167 | Phi-4 | 14B | INT4 Q8 | 59 tok/s 36 tok/s | ~981 ms ~993 ms | |
#168 | Gemma 3 27B | 27B | INT4 | 34 tok/s | ~1.9s | |
#170 | DeepSeek-R1 32B | 32B | INT4 | 30 tok/s | ~2.2s | |
#172 | Qwen3-32B | 32B | INT4 | 29 tok/s | ~2.2s | |
#176 | Magistral Small | 24B | INT4 | 29 tok/s | ~1.7s | |
#177 | Qwen2.5-32B | 32B | INT4 | 29 tok/s | ~2.2s | |
#178 | OLMo 3.1 32B Instruct | 32B | INT4 | 20 tok/s | ~2.6s | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 61 tok/s 36 tok/s | ~981 ms ~992 ms | |
#180 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 74 tok/s 53 tok/s 32 tok/s | ~504 ms ~510 ms ~522 ms | |
#184 | Ministral 3 14B | 14B | INT4 Q8 | 44 tok/s 30 tok/s | ~987 ms ~998 ms | |
#187 | Gemma 3 12B | 12B | INT4 Q8 FP16 | 67 tok/s 41 tok/s 20 tok/s | ~844 ms ~854 ms ~1.0s | |
#189 | Mistral-Small-2501 | 24B | INT4 | 37 tok/s | ~1.7s | |
#190 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 68 tok/s 48 tok/s 27 tok/s | ~573 ms ~579 ms ~642 ms | |
#191 | Gemma 4 31B | 30.7B | INT4 | 30 tok/s | ~2.1s | |
#192 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~160 ms ~162 ms ~165 ms | |
#193 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~160 ms ~162 ms ~165 ms | |
#194 | Gemma 2 27B | 27B | INT4 | 34 tok/s | ~1.9s | |
#195 | Qwen2.5-14B | 14B | INT4 Q8 | 59 tok/s 36 tok/s | ~981 ms ~993 ms | |
#196 | Nemotron 3.5 Lightning | 30B (3B active) | INT4 | 58 tok/s | ~330 ms | |
#197 | OLMo 3.1 32B Think | 32B | INT4 | 20 tok/s | ~2.6s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 125 tok/s 83 tok/s 48 tok/s | ~371 ms ~375 ms ~384 ms | |
#203 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 94 tok/s 59 tok/s 32 tok/s | ~569 ms ~575 ms ~589 ms | |
#205 | Qwen3-4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~296 ms ~299 ms ~306 ms | |
#206 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 120 tok/s 95 tok/s 63 tok/s | ~231 ms ~233 ms ~238 ms | |
#207 | OLMo 3 32B Base | 32B | INT4 | 20 tok/s | ~2.6s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 278 tok/s 237 tok/s 178 tok/s | ~69 ms ~70 ms ~71 ms | |
#209 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 84 tok/s 53 tok/s 27 tok/s | ~638 ms ~645 ms ~716 ms | |
#210 | Qwen3-14B | 14B | INT4 Q8 | 59 tok/s 36 tok/s | ~981 ms ~993 ms | |
#211 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~296 ms ~299 ms ~306 ms | |
#212 | Qwen3-8B | 8B | INT4 Q8 FP16 | 92 tok/s 58 tok/s 32 tok/s | ~569 ms ~575 ms ~589 ms | |
#214 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 104 tok/s 66 tok/s 36 tok/s | ~500 ms ~506 ms ~518 ms | |
#215 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 217 tok/s 168 tok/s 112 tok/s | ~138 ms ~139 ms ~142 ms | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 311 tok/s 293 tok/s 257 tok/s | ~28 ms ~28 ms ~29 ms | |
#217 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 92 tok/s 58 tok/s 32 tok/s | ~569 ms ~575 ms ~589 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 298 tok/s 261 tok/s 205 tok/s | ~53 ms ~54 ms ~55 ms | |
#219 | Command R | 35B | INT4 | 19 tok/s | ~2.8s | |
#220 | Llama 3 8B | 8B | INT4 Q8 FP16 | 92 tok/s 58 tok/s 32 tok/s | ~569 ms ~575 ms ~589 ms | |
#222 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 149 tok/s 103 tok/s 61 tok/s | ~283 ms ~286 ms ~292 ms | |
#224 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 101 tok/s 65 tok/s 36 tok/s | ~501 ms ~506 ms ~519 ms | |
#225 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 92 tok/s 58 tok/s 32 tok/s | ~569 ms ~575 ms ~589 ms | |
#226 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 228 tok/s 180 tok/s 122 tok/s | ~123 ms ~124 ms ~127 ms | |
#227 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~228 ms ~230 ms ~236 ms | |
#228 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 | 145 tok/s | ~296 ms | |
#229 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 149 tok/s 103 tok/s 61 tok/s | ~283 ms ~286 ms ~292 ms | |
#230 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 119 tok/s 103 tok/s 76 tok/s | ~174 ms ~175 ms ~179 ms | |
#231 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 98 tok/s 63 tok/s 35 tok/s | ~521 ms ~527 ms ~539 ms | |
#232 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 260 tok/s 216 tok/s 157 tok/s | ~86 ms ~87 ms ~89 ms | |
#233 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~160 ms ~162 ms ~165 ms | |
#234 | Phi-3-medium | 14B | INT4 Q8 | 59 tok/s 36 tok/s | ~981 ms ~993 ms | |
#235 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 74 tok/s 53 tok/s 32 tok/s | ~504 ms ~510 ms ~522 ms | |
#236 | Yi-34B | 34B | INT4 | 19 tok/s | ~2.7s | |
#237 | Qwen2-7B | 7B | INT4 Q8 FP16 | 101 tok/s 65 tok/s 36 tok/s | ~501 ms ~506 ms ~519 ms | |
#238 | Phi-3-small | 7B | INT4 Q8 FP16 | 101 tok/s 65 tok/s 36 tok/s | ~501 ms ~506 ms ~519 ms | |
#239 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 260 tok/s 216 tok/s 157 tok/s | ~86 ms ~87 ms ~89 ms | |
#240 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 98 tok/s 63 tok/s 35 tok/s | ~521 ms ~527 ms ~539 ms | |
#242 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 74 tok/s 53 tok/s 32 tok/s | ~504 ms ~510 ms ~522 ms | |
#243 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 214 tok/s 159 tok/s 102 tok/s | ~160 ms ~162 ms ~165 ms | |
#244 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 82 tok/s 60 tok/s 37 tok/s | ~436 ms ~440 ms ~451 ms | |
#245 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 82 tok/s 60 tok/s 37 tok/s | ~436 ms ~440 ms ~451 ms | |
#246 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 82 tok/s 60 tok/s 37 tok/s | ~436 ms ~440 ms ~451 ms | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 331 tok/s 307 tok/s 264 tok/s | ~30 ms ~30 ms ~31 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 308 tok/s 275 tok/s 221 tok/s | ~45 ms ~46 ms ~46 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 308 tok/s 275 tok/s 221 tok/s | ~45 ms ~46 ms ~46 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 304 tok/s 285 tok/s 248 tok/s | ~30 ms ~30 ms ~31 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 304 tok/s 285 tok/s 248 tok/s | ~30 ms ~30 ms ~31 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 298 tok/s 261 tok/s 205 tok/s | ~53 ms ~54 ms ~55 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 297 tok/s 260 tok/s 203 tok/s | ~54 ms ~54 ms ~55 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 297 tok/s 260 tok/s 203 tok/s | ~54 ms ~54 ms ~55 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 294 tok/s 257 tok/s 200 tok/s | ~56 ms ~56 ms ~57 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 273 tok/s 230 tok/s 171 tok/s | ~74 ms ~75 ms ~76 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 273 tok/s 230 tok/s 171 tok/s | ~74 ms ~75 ms ~76 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 273 tok/s 230 tok/s 171 tok/s | ~74 ms ~75 ms ~76 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 270 tok/s 223 tok/s 160 tok/s | ~86 ms ~87 ms ~89 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 260 tok/s 216 tok/s 157 tok/s | ~86 ms ~87 ms ~89 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 260 tok/s 216 tok/s 157 tok/s | ~86 ms ~87 ms ~89 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 245 tok/s 199 tok/s 139 tok/s | ~103 ms ~103 ms ~106 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 240 tok/s 193 tok/s 134 tok/s | ~108 ms ~109 ms ~111 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 228 tok/s 180 tok/s 122 tok/s | ~123 ms ~124 ms ~127 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 228 tok/s 180 tok/s 122 tok/s | ~123 ms ~124 ms ~127 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 228 tok/s 180 tok/s 122 tok/s | ~123 ms ~124 ms ~127 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 228 tok/s 180 tok/s 122 tok/s | ~123 ms ~124 ms ~127 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 217 tok/s 168 tok/s 112 tok/s | ~138 ms ~139 ms ~142 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 217 tok/s 168 tok/s 112 tok/s | ~138 ms ~139 ms ~142 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 217 tok/s 168 tok/s 112 tok/s | ~138 ms ~139 ms ~142 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 213 tok/s 164 tok/s 108 tok/s | ~145 ms ~147 ms ~150 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~160 ms ~162 ms ~165 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~160 ms ~162 ms ~165 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~160 ms ~162 ms ~165 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~160 ms ~162 ms ~165 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~160 ms ~162 ms ~165 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~160 ms ~162 ms ~165 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 FP16 | 203 tok/s 154 tok/s 95 tok/s | ~180 ms ~181 ms ~200 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~160 ms ~162 ms ~165 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 199 tok/s 150 tok/s 97 tok/s | ~167 ms ~169 ms ~172 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 195 tok/s 146 tok/s 93 tok/s | ~174 ms ~176 ms ~180 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 191 tok/s 142 tok/s 90 tok/s | ~181 ms ~183 ms ~187 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 185 tok/s 135 tok/s 85 tok/s | ~194 ms ~196 ms ~201 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 183 tok/s 133 tok/s 84 tok/s | ~198 ms ~200 ms ~205 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 183 tok/s 133 tok/s 84 tok/s | ~198 ms ~200 ms ~205 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 177 tok/s 125 tok/s 75 tok/s | ~228 ms ~230 ms ~235 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 175 tok/s 151 tok/s 112 tok/s | ~110 ms ~110 ms ~113 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 175 tok/s 151 tok/s 112 tok/s | ~110 ms ~110 ms ~113 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 175 tok/s 151 tok/s 112 tok/s | ~110 ms ~110 ms ~113 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 FP16 | 172 tok/s 129 tok/s 74 tok/s | ~223 ms ~225 ms ~268 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 171 tok/s 122 tok/s 74 tok/s | ~228 ms ~230 ms ~236 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~228 ms ~230 ms ~236 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~228 ms ~230 ms ~236 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~228 ms ~230 ms ~236 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~228 ms ~230 ms ~236 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~228 ms ~230 ms ~236 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~228 ms ~230 ms ~236 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 160 tok/s | ~252 ms | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 Q8 | 151 tok/s 101 tok/s | ~277 ms ~327 ms | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 Q8 | 151 tok/s 101 tok/s | ~277 ms ~327 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 146 tok/s | ~291 ms | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 146 tok/s | ~291 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~296 ms ~299 ms ~306 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~296 ms ~299 ms ~306 ms | |
- | Hy-Memory 30B A3B | 30B (3B active) | INT4 | 145 tok/s | ~296 ms | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 | 145 tok/s | ~296 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~296 ms ~299 ms ~306 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~296 ms ~299 ms ~306 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 140 tok/s 117 tok/s 83 tok/s | ~163 ms ~164 ms ~168 ms | |
- | MiniCPM-V 4.7 35B A3B | 35B (3B active) | INT4 | 136 tok/s | ~327 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 127 tok/s 84 tok/s 49 tok/s | ~364 ms ~368 ms ~377 ms | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 127 tok/s 84 tok/s 49 tok/s | ~364 ms ~368 ms ~377 ms | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 127 tok/s 84 tok/s 49 tok/s | ~364 ms ~368 ms ~377 ms | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 125 tok/s 101 tok/s 68 tok/s | ~210 ms ~212 ms ~217 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 120 tok/s 95 tok/s 63 tok/s | ~231 ms ~233 ms ~238 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 120 tok/s 95 tok/s 63 tok/s | ~231 ms ~233 ms ~238 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 105 tok/s 66 tok/s 37 tok/s | ~500 ms ~506 ms ~518 ms | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 103 tok/s 66 tok/s 37 tok/s | ~487 ms ~493 ms ~504 ms | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 103 tok/s 66 tok/s 37 tok/s | ~487 ms ~493 ms ~504 ms | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 101 tok/s 65 tok/s 36 tok/s | ~501 ms ~506 ms ~519 ms | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 101 tok/s 65 tok/s 36 tok/s | ~501 ms ~506 ms ~519 ms | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 98 tok/s 63 tok/s 35 tok/s | ~521 ms ~527 ms ~539 ms | |
- | Youtu Parsing Omni | 8B | INT4 Q8 FP16 | 94 tok/s 59 tok/s 32 tok/s | ~569 ms ~575 ms ~589 ms | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 FP16 | 91 tok/s 58 tok/s 32 tok/s | ~576 ms ~582 ms ~596 ms | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 FP16 | 91 tok/s 58 tok/s 32 tok/s | ~576 ms ~582 ms ~596 ms | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 FP16 | 84 tok/s 53 tok/s 27 tok/s | ~638 ms ~645 ms ~716 ms | |
- | LensVLM 9B | 9B | INT4 Q8 FP16 | 84 tok/s 53 tok/s 27 tok/s | ~638 ms ~645 ms ~716 ms | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 FP16 | 84 tok/s 53 tok/s 27 tok/s | ~638 ms ~645 ms ~716 ms | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 82 tok/s 60 tok/s 37 tok/s | ~436 ms ~440 ms ~451 ms | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 82 tok/s 60 tok/s 37 tok/s | ~436 ms ~440 ms ~451 ms | |
- | Falcon3-10B | 10B | INT4 Q8 FP16 | 78 tok/s 48 tok/s 25 tok/s | ~706 ms ~714 ms ~793 ms | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 Q8 | 78 tok/s 65 tok/s | ~273 ms ~297 ms | |
- | Mochi 1 Preview | 10B | INT4 Q8 FP16 | 78 tok/s 48 tok/s 25 tok/s | ~706 ms ~714 ms ~793 ms | |
- | Falcon2-11B | 11B | INT4 Q8 FP16 | 75 tok/s 45 tok/s 22 tok/s | ~774 ms ~783 ms ~939 ms | |
- | Hunyuan Lite | 7B | INT4 Q8 FP16 | 74 tok/s 53 tok/s 32 tok/s | ~504 ms ~510 ms ~522 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 FP16 | 74 tok/s 53 tok/s 32 tok/s | ~504 ms ~510 ms ~522 ms | |
- | SEA-LION-7B | 7.1B | INT4 Q8 FP16 | 74 tok/s 53 tok/s 32 tok/s | ~511 ms ~516 ms ~529 ms | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 FP16 | 74 tok/s 53 tok/s 32 tok/s | ~511 ms ~516 ms ~529 ms | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 FP16 | 68 tok/s 41 tok/s 20 tok/s | ~838 ms ~847 ms ~1.0s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 FP16 | 68 tok/s 41 tok/s 20 tok/s | ~838 ms ~847 ms ~1.0s | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 FP16 | 68 tok/s 41 tok/s 20 tok/s | ~838 ms ~847 ms ~1.0s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 FP16 | 68 tok/s 41 tok/s 20 tok/s | ~838 ms ~847 ms ~1.0s | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 FP16 | 68 tok/s 41 tok/s 20 tok/s | ~838 ms ~847 ms ~1.0s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 FP16 | 68 tok/s 48 tok/s 27 tok/s | ~573 ms ~579 ms ~642 ms | |
- | Typhoon-2-8B | 8B | INT4 Q8 FP16 | 68 tok/s 48 tok/s 27 tok/s | ~573 ms ~579 ms ~642 ms | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 63 tok/s 38 tok/s | ~913 ms ~923 ms | |
- | GLM-4-9B | 9B | INT4 Q8 FP16 | 62 tok/s 44 tok/s 25 tok/s | ~642 ms ~649 ms ~721 ms | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 FP16 | 62 tok/s 44 tok/s 25 tok/s | ~642 ms ~649 ms ~721 ms | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 FP16 | 62 tok/s 44 tok/s 25 tok/s | ~642 ms ~649 ms ~721 ms | |
- | Yi-9B | 9B | INT4 Q8 FP16 | 62 tok/s 44 tok/s 25 tok/s | ~642 ms ~649 ms ~721 ms | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 FP16 | 61 tok/s 43 tok/s 24 tok/s | ~656 ms ~663 ms ~736 ms | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 FP16 | 61 tok/s 43 tok/s 24 tok/s | ~656 ms ~663 ms ~736 ms | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 59 tok/s 36 tok/s | ~981 ms ~993 ms | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 59 tok/s 36 tok/s | ~981 ms ~993 ms | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 59 tok/s 36 tok/s | ~981 ms ~993 ms | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 56 tok/s 34 tok/s | ~1.0s ~1.1s | |
- | GreenMind-14B-R1 | 14B | INT4 Q8 | 44 tok/s 30 tok/s | ~987 ms ~998 ms | |
- | Arete 27B | 27B | INT4 | 34 tok/s | ~1.9s | |
- | AREX-2 | 27B | INT4 | 34 tok/s | ~1.9s | |
- | PPLX Decider v1 27B | 27B | INT4 | 34 tok/s | ~1.9s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 34 tok/s | ~1.9s | |
- | Agnes 3.0 Flash | 33B | INT4 | 28 tok/s | ~2.3s | |
- | Falcon-40B | 40B | INT4 | 23 tok/s | ~3.0s | |
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 PRO 4000 Blackwell (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 672 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 149 tok/s on an 8B Q4 model and 18 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning