NVIDIA RTX 4500 Blackwell (32GB)
The NVIDIA RTX 4500 Blackwell (32GB) features 32 GB of dedicated VRAM and 896 GB/s memory bandwidth, supporting CUDA and TensorRT-LLM runtimes for full-precision and quantized inference.
Memory
32 GB
Usable Memory Ceiling
32 GB
Bandwidth
896 GB/s
Max Inference Class
32B Models (Q4)
TDP
175W
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 4500 Blackwell (32GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA RTX 4500 Blackwell (32GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#48 | Qwen 3.8 27B | 27B | INT4 Q8 | 44 tok/s 24 tok/s | ~1.5s ~1.6s | |
#83 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 | 150 tok/s | ~293 ms | |
#93 | Qwen3.5-27B | 27B | INT4 Q8 | 44 tok/s 24 tok/s | ~1.5s ~1.6s | |
#105 | Sarvam-30B | 32B (2.4B active) | INT4 | 184 tok/s | ~206 ms | |
#106 | Qwen3.6 35B A3B | 35B (3B active) | INT4 | 169 tok/s | ~239 ms | |
#110 | Muse Glimmer 30B | 30B | INT4 Q8 | 40 tok/s 21 tok/s | ~1.6s ~1.9s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 Q8 | 4 tok/s 2 tok/s | ~16.0s ~16.2s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 Q8 FP16 | 56 tok/s 39 tok/s 20 tok/s | ~781 ms ~789 ms ~944 ms | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 Q8 | 158 tok/s 112 tok/s | ~268 ms ~293 ms | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 104 tok/s 67 tok/s 37 tok/s | ~505 ms ~510 ms ~522 ms | |
#126 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 | 169 tok/s | ~239 ms | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 124 tok/s 82 tok/s 47 tok/s | ~397 ms ~401 ms ~410 ms | |
#135 | Gemma 4 12B | 11.95B | INT4 Q8 FP16 | 64 tok/s 44 tok/s 25 tok/s | ~669 ms ~676 ms ~750 ms | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 171 tok/s 122 tok/s 74 tok/s | ~235 ms ~238 ms ~243 ms | |
#143 | GPT-OSS 20B | 21B (3.6B active) | INT4 Q8 | 86 tok/s 71 tok/s | ~257 ms ~280 ms | |
#144 | GLM-4V | 9B | INT4 Q8 FP16 | 78 tok/s 56 tok/s 34 tok/s | ~508 ms ~513 ms ~525 ms | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 38 tok/s 23 tok/s 12 tok/s | ~1.6s ~1.6s ~1.6s | |
#153 | Qwen3-30B-A3B | 30B (3B active) | INT4 Q8 | 171 tok/s 119 tok/s | ~235 ms ~277 ms | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~450 ms ~455 ms ~466 ms | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~450 ms ~455 ms ~466 ms | |
#163 | Mistral Large 3 | 41B (675B active) | INT4 | 2 tok/s | ~41.0s | |
#165 | GLM-4 | 32B | INT4 | 30 tok/s | ~1.7s | |
#166 | Phi-4 | 14B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 24 tok/s | ~776 ms ~785 ms ~870 ms | |
#167 | Gemma 3 27B | 27B | INT4 Q8 | 44 tok/s 24 tok/s | ~1.5s ~1.6s | |
#170 | DeepSeek-R1 32B | 32B | INT4 Q8 | 39 tok/s 20 tok/s | ~1.7s ~2.1s | |
#171 | Qwen3-32B | 32B | INT4 | 38 tok/s | ~1.7s | |
#175 | Magistral Small | 24B | INT4 Q8 | 37 tok/s 23 tok/s | ~1.3s ~1.4s | |
#176 | OLMo 3.1 32B Instruct | 32B | INT4 | 30 tok/s | ~1.7s | |
#177 | Qwen2.5-32B | 32B | INT4 | 38 tok/s | ~1.7s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 93 tok/s 68 tok/s 42 tok/s | ~399 ms ~403 ms ~413 ms | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 FP16 | 77 tok/s 47 tok/s 24 tok/s | ~776 ms ~784 ms ~870 ms | |
#183 | Ministral 3 14B | 14B | INT4 Q8 FP16 | 56 tok/s 39 tok/s 20 tok/s | ~781 ms ~789 ms ~944 ms | |
#186 | Gemma 3 12B | 12B | INT4 Q8 FP16 | 85 tok/s 53 tok/s 29 tok/s | ~668 ms ~675 ms ~691 ms | |
#188 | Mistral-Small-2501 | 24B | INT4 Q8 | 48 tok/s 27 tok/s | ~1.3s ~1.4s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 85 tok/s 62 tok/s 37 tok/s | ~453 ms ~458 ms ~468 ms | |
#190 | Gemma 4 31B | 30.7B | INT4 Q8 | 39 tok/s 20 tok/s | ~1.7s ~2.0s | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~128 ms ~129 ms ~132 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~128 ms ~129 ms ~132 ms | |
#193 | Gemma 2 27B | 27B | INT4 Q8 | 44 tok/s 24 tok/s | ~1.5s ~1.6s | |
#194 | Qwen2.5-14B | 14B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 24 tok/s | ~776 ms ~785 ms ~870 ms | |
#195 | OLMo 3.1 32B Think | 32B | INT4 | 30 tok/s | ~1.7s | |
#196 | Nemotron 3.5 Lightning | 30B (3B active) | INT4 | 78 tok/s | ~242 ms | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 150 tok/s 103 tok/s 61 tok/s | ~295 ms ~298 ms ~304 ms | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 116 tok/s 75 tok/s 42 tok/s | ~450 ms ~455 ms ~466 ms | |
#203 | Kimi Linear 48B A3B Instruct | 48B (3B active) | INT4 | 60 tok/s | ~306 ms | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 171 tok/s 122 tok/s 74 tok/s | ~235 ms ~238 ms ~243 ms | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 144 tok/s 117 tok/s 80 tok/s | ~183 ms ~185 ms ~189 ms | |
#206 | OLMo 3 32B Base | 32B | INT4 | 30 tok/s | ~1.7s | |
#207 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 104 tok/s 67 tok/s 37 tok/s | ~505 ms ~510 ms ~522 ms | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 297 tok/s 260 tok/s 204 tok/s | ~56 ms ~57 ms ~58 ms | |
#209 | Qwen3-14B | 14B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 24 tok/s | ~776 ms ~785 ms ~870 ms | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 171 tok/s 122 tok/s 74 tok/s | ~235 ms ~238 ms ~243 ms | |
#211 | Qwen3-8B | 8B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~450 ms ~455 ms ~466 ms | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 126 tok/s 83 tok/s 47 tok/s | ~397 ms ~401 ms ~410 ms | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 242 tok/s 195 tok/s 136 tok/s | ~111 ms ~112 ms ~114 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~450 ms ~455 ms ~466 ms | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 324 tok/s 309 tok/s 279 tok/s | ~24 ms ~24 ms ~24 ms | |
#217 | Command R | 35B | INT4 | 28 tok/s | ~1.9s | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 313 tok/s 282 tok/s 231 tok/s | ~44 ms ~44 ms ~45 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~450 ms ~455 ms ~466 ms | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 175 tok/s 126 tok/s 77 tok/s | ~225 ms ~227 ms ~232 ms | |
#222 | Mixtral-8x7B-v0.1 | 46.7B (7B active) | INT4 | 106 tok/s | ~498 ms | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 124 tok/s 82 tok/s 47 tok/s | ~397 ms ~401 ms ~410 ms | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 113 tok/s 74 tok/s 42 tok/s | ~450 ms ~455 ms ~466 ms | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 253 tok/s 206 tok/s 147 tok/s | ~99 ms ~100 ms ~102 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 196 tok/s 145 tok/s 92 tok/s | ~182 ms ~183 ms ~187 ms | |
#227 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 Q8 | 171 tok/s 119 tok/s | ~235 ms ~277 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 175 tok/s 126 tok/s 77 tok/s | ~225 ms ~227 ms ~232 ms | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 144 tok/s 126 tok/s 95 tok/s | ~139 ms ~140 ms ~142 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 121 tok/s 79 tok/s 45 tok/s | ~413 ms ~417 ms ~427 ms | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 281 tok/s 241 tok/s 183 tok/s | ~70 ms ~70 ms ~72 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~128 ms ~129 ms ~132 ms | |
#233 | Phi-3-medium | 14B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 24 tok/s | ~776 ms ~785 ms ~870 ms | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 93 tok/s 68 tok/s 42 tok/s | ~399 ms ~403 ms ~413 ms | |
#235 | Yi-34B | 34B | INT4 | 28 tok/s | ~1.8s | |
#236 | Qwen2-7B | 7B | INT4 Q8 FP16 | 124 tok/s 82 tok/s 47 tok/s | ~397 ms ~401 ms ~410 ms | |
#237 | Phi-3-small | 7B | INT4 Q8 FP16 | 124 tok/s 82 tok/s 47 tok/s | ~397 ms ~401 ms ~410 ms | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 281 tok/s 241 tok/s 183 tok/s | ~70 ms ~70 ms ~72 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 121 tok/s 79 tok/s 45 tok/s | ~413 ms ~417 ms ~427 ms | |
#241 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 93 tok/s 68 tok/s 42 tok/s | ~399 ms ~403 ms ~413 ms | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 239 tok/s 186 tok/s 125 tok/s | ~128 ms ~129 ms ~132 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 102 tok/s 76 tok/s 47 tok/s | ~345 ms ~349 ms ~357 ms | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 102 tok/s 76 tok/s 47 tok/s | ~345 ms ~349 ms ~357 ms | |
#245 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 102 tok/s 76 tok/s 47 tok/s | ~345 ms ~349 ms ~357 ms | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 340 tok/s 321 tok/s 285 tok/s | ~25 ms ~25 ms ~26 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 322 tok/s 294 tok/s 246 tok/s | ~37 ms ~38 ms ~38 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 322 tok/s 294 tok/s 246 tok/s | ~37 ms ~38 ms ~38 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 318 tok/s 303 tok/s 270 tok/s | ~25 ms ~26 ms ~26 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 318 tok/s 303 tok/s 270 tok/s | ~25 ms ~26 ms ~26 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 313 tok/s 282 tok/s 231 tok/s | ~44 ms ~44 ms ~45 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 312 tok/s 281 tok/s 229 tok/s | ~44 ms ~44 ms ~45 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 312 tok/s 281 tok/s 229 tok/s | ~44 ms ~44 ms ~45 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 310 tok/s 278 tok/s 226 tok/s | ~45 ms ~46 ms ~47 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 292 tok/s 254 tok/s 198 tok/s | ~60 ms ~61 ms ~62 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 292 tok/s 254 tok/s 198 tok/s | ~60 ms ~61 ms ~62 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 292 tok/s 254 tok/s 198 tok/s | ~60 ms ~61 ms ~62 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 290 tok/s 247 tok/s 187 tok/s | ~69 ms ~70 ms ~71 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 281 tok/s 241 tok/s 183 tok/s | ~70 ms ~70 ms ~72 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 281 tok/s 241 tok/s 183 tok/s | ~70 ms ~70 ms ~72 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 268 tok/s 225 tok/s 165 tok/s | ~82 ms ~83 ms ~85 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 264 tok/s 219 tok/s 160 tok/s | ~87 ms ~88 ms ~89 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 253 tok/s 206 tok/s 147 tok/s | ~99 ms ~100 ms ~102 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 253 tok/s 206 tok/s 147 tok/s | ~99 ms ~100 ms ~102 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 253 tok/s 206 tok/s 147 tok/s | ~99 ms ~100 ms ~102 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 253 tok/s 206 tok/s 147 tok/s | ~99 ms ~100 ms ~102 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 242 tok/s 195 tok/s 136 tok/s | ~111 ms ~112 ms ~114 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 242 tok/s 195 tok/s 136 tok/s | ~111 ms ~112 ms ~114 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 242 tok/s 195 tok/s 136 tok/s | ~111 ms ~112 ms ~114 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 238 tok/s 190 tok/s 131 tok/s | ~116 ms ~117 ms ~120 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~128 ms ~129 ms ~132 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~128 ms ~129 ms ~132 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~128 ms ~129 ms ~132 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~128 ms ~129 ms ~132 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~128 ms ~129 ms ~132 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~128 ms ~129 ms ~132 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~143 ms ~144 ms ~147 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~128 ms ~129 ms ~132 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 225 tok/s 176 tok/s 119 tok/s | ~133 ms ~135 ms ~137 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 222 tok/s 172 tok/s 115 tok/s | ~139 ms ~140 ms ~143 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 218 tok/s 168 tok/s 111 tok/s | ~145 ms ~146 ms ~149 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 211 tok/s 161 tok/s 105 tok/s | ~155 ms ~156 ms ~160 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 209 tok/s 159 tok/s 104 tok/s | ~158 ms ~160 ms ~163 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 209 tok/s 159 tok/s 104 tok/s | ~158 ms ~160 ms ~163 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 204 tok/s 149 tok/s 94 tok/s | ~181 ms ~183 ms ~187 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 201 tok/s 177 tok/s 136 tok/s | ~88 ms ~89 ms ~90 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 201 tok/s 177 tok/s 136 tok/s | ~88 ms ~89 ms ~90 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 201 tok/s 177 tok/s 136 tok/s | ~88 ms ~89 ms ~90 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 198 tok/s 146 tok/s 93 tok/s | ~182 ms ~183 ms ~187 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 FP16 | 198 tok/s 154 tok/s 102 tok/s | ~177 ms ~179 ms ~182 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 196 tok/s 145 tok/s 92 tok/s | ~182 ms ~183 ms ~187 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 196 tok/s 145 tok/s 92 tok/s | ~182 ms ~183 ms ~187 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 196 tok/s 145 tok/s 92 tok/s | ~182 ms ~183 ms ~187 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 196 tok/s 145 tok/s 92 tok/s | ~182 ms ~183 ms ~187 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 196 tok/s 145 tok/s 92 tok/s | ~182 ms ~183 ms ~187 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 196 tok/s 145 tok/s 92 tok/s | ~182 ms ~183 ms ~187 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 Q8 | 186 tok/s 140 tok/s | ~200 ms ~218 ms | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 Q8 | 177 tok/s 136 tok/s | ~220 ms ~222 ms | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 Q8 | 177 tok/s 136 tok/s | ~220 ms ~222 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 Q8 | 172 tok/s 126 tok/s | ~231 ms ~252 ms | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 Q8 | 172 tok/s 126 tok/s | ~231 ms ~252 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 171 tok/s 122 tok/s 74 tok/s | ~235 ms ~238 ms ~243 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 171 tok/s 122 tok/s 74 tok/s | ~235 ms ~238 ms ~243 ms | |
- | Hy-Memory 30B A3B | 30B (3B active) | INT4 Q8 | 171 tok/s 119 tok/s | ~235 ms ~277 ms | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 Q8 | 171 tok/s 119 tok/s | ~235 ms ~277 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 171 tok/s 122 tok/s 74 tok/s | ~235 ms ~238 ms ~243 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 171 tok/s 122 tok/s 74 tok/s | ~235 ms ~238 ms ~243 ms | |
- | MiniCPM-V 4.7 35B A3B | 35B (3B active) | INT4 | 169 tok/s | ~239 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 165 tok/s 141 tok/s 103 tok/s | ~130 ms ~131 ms ~134 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 152 tok/s 105 tok/s 62 tok/s | ~289 ms ~292 ms ~299 ms | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 152 tok/s 105 tok/s 62 tok/s | ~289 ms ~292 ms ~299 ms | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 152 tok/s 105 tok/s 62 tok/s | ~289 ms ~292 ms ~299 ms | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 150 tok/s 123 tok/s 86 tok/s | ~167 ms ~169 ms ~172 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 144 tok/s 117 tok/s 80 tok/s | ~183 ms ~185 ms ~189 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 144 tok/s 117 tok/s 80 tok/s | ~183 ms ~185 ms ~189 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 128 tok/s 84 tok/s 47 tok/s | ~396 ms ~401 ms ~410 ms | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 126 tok/s 84 tok/s 48 tok/s | ~386 ms ~390 ms ~399 ms | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 126 tok/s 84 tok/s 48 tok/s | ~386 ms ~390 ms ~399 ms | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 124 tok/s 82 tok/s 47 tok/s | ~397 ms ~401 ms ~410 ms | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 124 tok/s 82 tok/s 47 tok/s | ~397 ms ~401 ms ~410 ms | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 121 tok/s 79 tok/s 45 tok/s | ~413 ms ~417 ms ~427 ms | |
- | Youtu Parsing Omni | 8B | INT4 Q8 FP16 | 116 tok/s 75 tok/s 42 tok/s | ~450 ms ~455 ms ~466 ms | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 FP16 | 112 tok/s 73 tok/s 41 tok/s | ~456 ms ~461 ms ~471 ms | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 FP16 | 112 tok/s 73 tok/s 41 tok/s | ~456 ms ~461 ms ~471 ms | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 FP16 | 104 tok/s 67 tok/s 37 tok/s | ~505 ms ~510 ms ~522 ms | |
- | LensVLM 9B | 9B | INT4 Q8 FP16 | 104 tok/s 67 tok/s 37 tok/s | ~505 ms ~510 ms ~522 ms | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 FP16 | 104 tok/s 67 tok/s 37 tok/s | ~505 ms ~510 ms ~522 ms | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 102 tok/s 76 tok/s 47 tok/s | ~345 ms ~349 ms ~357 ms | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 102 tok/s 76 tok/s 47 tok/s | ~345 ms ~349 ms ~357 ms | |
- | Falcon3-10B | 10B | INT4 Q8 FP16 | 97 tok/s 61 tok/s 34 tok/s | ~559 ms ~565 ms ~578 ms | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 Q8 | 97 tok/s 86 tok/s | ~216 ms ~218 ms | |
- | Mochi 1 Preview | 10B | INT4 Q8 FP16 | 97 tok/s 61 tok/s 34 tok/s | ~559 ms ~565 ms ~578 ms | |
- | Falcon2-11B | 11B | INT4 Q8 FP16 | 94 tok/s 58 tok/s 32 tok/s | ~613 ms ~619 ms ~634 ms | |
- | Hunyuan Lite | 7B | INT4 Q8 FP16 | 93 tok/s 68 tok/s 42 tok/s | ~399 ms ~403 ms ~413 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 FP16 | 93 tok/s 68 tok/s 42 tok/s | ~399 ms ~403 ms ~413 ms | |
- | SEA-LION-7B | 7.1B | INT4 Q8 FP16 | 92 tok/s 67 tok/s 41 tok/s | ~405 ms ~409 ms ~418 ms | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 FP16 | 92 tok/s 67 tok/s 41 tok/s | ~405 ms ~409 ms ~418 ms | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 FP16 | 85 tok/s 53 tok/s 29 tok/s | ~663 ms ~670 ms ~685 ms | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 FP16 | 85 tok/s 53 tok/s 29 tok/s | ~663 ms ~670 ms ~685 ms | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 FP16 | 85 tok/s 53 tok/s 29 tok/s | ~663 ms ~670 ms ~685 ms | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 FP16 | 85 tok/s 53 tok/s 29 tok/s | ~663 ms ~670 ms ~685 ms | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 FP16 | 85 tok/s 53 tok/s 29 tok/s | ~663 ms ~670 ms ~685 ms | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 FP16 | 85 tok/s 62 tok/s 37 tok/s | ~453 ms ~458 ms ~468 ms | |
- | Typhoon-2-8B | 8B | INT4 Q8 FP16 | 85 tok/s 62 tok/s 37 tok/s | ~453 ms ~458 ms ~468 ms | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 FP16 | 80 tok/s 49 tok/s 25 tok/s | ~722 ms ~730 ms ~810 ms | |
- | GLM-4-9B | 9B | INT4 Q8 FP16 | 78 tok/s 56 tok/s 34 tok/s | ~508 ms ~513 ms ~525 ms | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 FP16 | 78 tok/s 56 tok/s 34 tok/s | ~508 ms ~513 ms ~525 ms | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 FP16 | 78 tok/s 56 tok/s 34 tok/s | ~508 ms ~513 ms ~525 ms | |
- | Yi-9B | 9B | INT4 Q8 FP16 | 78 tok/s 56 tok/s 34 tok/s | ~508 ms ~513 ms ~525 ms | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 FP16 | 77 tok/s 55 tok/s 33 tok/s | ~519 ms ~524 ms ~536 ms | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 FP16 | 77 tok/s 55 tok/s 33 tok/s | ~519 ms ~524 ms ~536 ms | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 24 tok/s | ~776 ms ~785 ms ~870 ms | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 24 tok/s | ~776 ms ~785 ms ~870 ms | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 FP16 | 75 tok/s 46 tok/s 24 tok/s | ~776 ms ~785 ms ~870 ms | |
- | FLUX.2 Dev | 15B | INT4 Q8 FP16 | 71 tok/s 43 tok/s 21 tok/s | ~829 ms ~838 ms ~1.0s | |
- | GreenMind-14B-R1 | 14B | INT4 Q8 FP16 | 56 tok/s 39 tok/s 20 tok/s | ~781 ms ~789 ms ~944 ms | |
- | Arete 27B | 27B | INT4 Q8 | 44 tok/s 24 tok/s | ~1.5s ~1.6s | |
- | AREX-2 | 27B | INT4 Q8 | 44 tok/s 24 tok/s | ~1.5s ~1.6s | |
- | PPLX Decider v1 27B | 27B | INT4 Q8 | 44 tok/s 24 tok/s | ~1.5s ~1.6s | |
- | PPLX Decider v1.1 27B | 27B | INT4 Q8 | 44 tok/s 24 tok/s | ~1.5s ~1.6s | |
- | Agnes 3.0 Flash | 33B | INT4 | 37 tok/s | ~1.8s | |
- | Falcon-40B | 40B | INT4 | 32 tok/s | ~2.2s | |
Inference Capacity
Maximum model parameter class runnable by weight precision.
Context:
4-bit
32B Models
8-bit
14B 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
3B Models
Workload Recommendations
Guidance for optimal precision and operational ceilings on NVIDIA RTX 4500 Blackwell (32GB).
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 896 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 199 tok/s on an 8B Q4 model and 24 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning