NVIDIA RTX 3090 (24GB)
The NVIDIA RTX 3090 (24GB) features 24 GB of dedicated VRAM and 936 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
936.2 GB/s
Max Inference Class
32B Models (Q4)
TDP
350W
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 3090 (24GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA RTX 3090 (24GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#49 | Qwen 3.8 27B | 27B | INT4 | 45 tok/s | ~2.1s | |
#84 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 | 147 tok/s | ~445 ms | |
#94 | Qwen3.5-27B | 27B | INT4 | 45 tok/s | ~2.1s | |
#105 | Sarvam-30B | 32B (2.4B active) | INT4 | 188 tok/s | ~288 ms | |
#107 | Qwen3.6 35B A3B | 35B (3B active) | INT4 | 165 tok/s | ~363 ms | |
#109 | Muse Glimmer 30B | 30B | INT4 | 41 tok/s | ~2.3s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 Q8 | 5 tok/s 2 tok/s | ~22.6s ~24.7s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 Q8 | 59 tok/s 40 tok/s | ~1.1s ~1.1s | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 162 tok/s | ~376 ms | |
#124 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 108 tok/s 69 tok/s 37 tok/s | ~710 ms ~715 ms ~788 ms | |
#127 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 | 165 tok/s | ~363 ms | |
#129 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 127 tok/s 85 tok/s 48 tok/s | ~557 ms ~561 ms ~570 ms | |
#136 | Gemma 4 12B | 11.95B | INT4 Q8 | 66 tok/s 46 tok/s | ~940 ms ~946 ms | |
#141 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 175 tok/s 125 tok/s 77 tok/s | ~329 ms ~331 ms ~336 ms | |
#144 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 88 tok/s | ~357 ms | |
#146 | GLM-4V | 9B | INT4 Q8 FP16 | 81 tok/s 58 tok/s 33 tok/s | ~713 ms ~718 ms ~791 ms | |
#151 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 39 tok/s 24 tok/s 12 tok/s | ~2.2s ~2.2s ~2.3s | |
#154 | Qwen3-30B-A3B | 30B (3B active) | INT4 | 175 tok/s | ~328 ms | |
#159 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 117 tok/s 76 tok/s 43 tok/s | ~633 ms ~637 ms ~647 ms | |
#160 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 117 tok/s 76 tok/s 43 tok/s | ~633 ms ~637 ms ~647 ms | |
#166 | GLM-4 | 32B | INT4 | 28 tok/s | ~2.9s | |
#167 | Phi-4 | 14B | INT4 Q8 | 78 tok/s 48 tok/s | ~1.1s ~1.1s | |
#168 | Gemma 3 27B | 27B | INT4 | 45 tok/s | ~2.1s | |
#170 | DeepSeek-R1 32B | 32B | INT4 | 40 tok/s | ~2.4s | |
#172 | Qwen3-32B | 32B | INT4 | 39 tok/s | ~2.4s | |
#176 | Magistral Small | 24B | INT4 | 39 tok/s | ~1.9s | |
#177 | Qwen2.5-32B | 32B | INT4 | 39 tok/s | ~2.4s | |
#178 | OLMo 3.1 32B Instruct | 32B | INT4 | 28 tok/s | ~2.9s | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 80 tok/s 49 tok/s | ~1.1s ~1.1s | |
#180 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 96 tok/s 70 tok/s 43 tok/s | ~559 ms ~563 ms ~572 ms | |
#184 | Ministral 3 14B | 14B | INT4 Q8 | 59 tok/s 40 tok/s | ~1.1s ~1.1s | |
#187 | Gemma 3 12B | 12B | INT4 Q8 FP16 | 87 tok/s 55 tok/s 27 tok/s | ~940 ms ~946 ms ~1.1s | |
#189 | Mistral-Small-2501 | 24B | INT4 | 50 tok/s | ~1.8s | |
#190 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 88 tok/s 64 tok/s 37 tok/s | ~635 ms ~640 ms ~705 ms | |
#191 | Gemma 4 31B | 30.7B | INT4 | 41 tok/s | ~2.3s | |
#192 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 233 tok/s 184 tok/s 126 tok/s | ~178 ms ~179 ms ~181 ms | |
#193 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 233 tok/s 184 tok/s 126 tok/s | ~178 ms ~179 ms ~181 ms | |
#194 | Gemma 2 27B | 27B | INT4 | 45 tok/s | ~2.1s | |
#195 | Qwen2.5-14B | 14B | INT4 Q8 | 78 tok/s 48 tok/s | ~1.1s ~1.1s | |
#196 | Nemotron 3.5 Lightning | 30B (3B active) | INT4 | 76 tok/s | ~363 ms | |
#197 | OLMo 3.1 32B Think | 32B | INT4 | 28 tok/s | ~2.9s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 154 tok/s 106 tok/s 63 tok/s | ~413 ms ~415 ms ~422 ms | |
#203 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 119 tok/s 77 tok/s 43 tok/s | ~632 ms ~637 ms ~647 ms | |
#205 | Qwen3-4B | 4B | INT4 Q8 FP16 | 175 tok/s 125 tok/s 77 tok/s | ~329 ms ~331 ms ~336 ms | |
#206 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 148 tok/s 120 tok/s 83 tok/s | ~255 ms ~256 ms ~260 ms | |
#207 | OLMo 3 32B Base | 32B | INT4 | 28 tok/s | ~2.9s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 299 tok/s 264 tok/s 208 tok/s | ~76 ms ~77 ms ~78 ms | |
#209 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 108 tok/s 69 tok/s 37 tok/s | ~710 ms ~715 ms ~788 ms | |
#210 | Qwen3-14B | 14B | INT4 Q8 | 78 tok/s 48 tok/s | ~1.1s ~1.1s | |
#211 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 175 tok/s 125 tok/s 77 tok/s | ~329 ms ~331 ms ~336 ms | |
#212 | Qwen3-8B | 8B | INT4 Q8 FP16 | 117 tok/s 76 tok/s 43 tok/s | ~633 ms ~637 ms ~647 ms | |
#214 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 130 tok/s 86 tok/s 49 tok/s | ~557 ms ~561 ms ~569 ms | |
#215 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 246 tok/s 199 tok/s 140 tok/s | ~153 ms ~154 ms ~156 ms | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 326 tok/s 311 tok/s 282 tok/s | ~30 ms ~30 ms ~31 ms | |
#217 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 117 tok/s 76 tok/s 43 tok/s | ~633 ms ~637 ms ~647 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 315 tok/s 285 tok/s 234 tok/s | ~58 ms ~59 ms ~59 ms | |
#219 | Command R | 35B | INT4 | 26 tok/s | ~3.1s | |
#220 | Llama 3 8B | 8B | INT4 Q8 FP16 | 117 tok/s 76 tok/s 43 tok/s | ~633 ms ~637 ms ~647 ms | |
#222 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 180 tok/s 129 tok/s 80 tok/s | ~314 ms ~316 ms ~321 ms | |
#224 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 127 tok/s 85 tok/s 48 tok/s | ~557 ms ~561 ms ~570 ms | |
#225 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 117 tok/s 76 tok/s 43 tok/s | ~633 ms ~637 ms ~647 ms | |
#226 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 256 tok/s 210 tok/s 151 tok/s | ~136 ms ~137 ms ~139 ms | |
#227 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 200 tok/s 149 tok/s 95 tok/s | ~253 ms ~255 ms ~259 ms | |
#228 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 | 175 tok/s | ~328 ms | |
#229 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 180 tok/s 129 tok/s 80 tok/s | ~314 ms ~316 ms ~321 ms | |
#230 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 148 tok/s 130 tok/s 98 tok/s | ~192 ms ~193 ms ~195 ms | |
#231 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 124 tok/s 82 tok/s 47 tok/s | ~579 ms ~583 ms ~593 ms | |
#232 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 284 tok/s 245 tok/s 187 tok/s | ~95 ms ~96 ms ~97 ms | |
#233 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 233 tok/s 184 tok/s 126 tok/s | ~178 ms ~179 ms ~181 ms | |
#234 | Phi-3-medium | 14B | INT4 Q8 | 78 tok/s 48 tok/s | ~1.1s ~1.1s | |
#235 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 96 tok/s 70 tok/s 43 tok/s | ~559 ms ~563 ms ~572 ms | |
#236 | Yi-34B | 34B | INT4 | 26 tok/s | ~3.1s | |
#237 | Qwen2-7B | 7B | INT4 Q8 FP16 | 127 tok/s 85 tok/s 48 tok/s | ~557 ms ~561 ms ~570 ms | |
#238 | Phi-3-small | 7B | INT4 Q8 FP16 | 127 tok/s 85 tok/s 48 tok/s | ~557 ms ~561 ms ~570 ms | |
#239 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 284 tok/s 245 tok/s 187 tok/s | ~95 ms ~96 ms ~97 ms | |
#240 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 124 tok/s 82 tok/s 47 tok/s | ~579 ms ~583 ms ~593 ms | |
#242 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 96 tok/s 70 tok/s 43 tok/s | ~559 ms ~563 ms ~572 ms | |
#243 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 243 tok/s 190 tok/s 129 tok/s | ~178 ms ~179 ms ~181 ms | |
#244 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 105 tok/s 79 tok/s 49 tok/s | ~483 ms ~486 ms ~494 ms | |
#245 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 105 tok/s 79 tok/s 49 tok/s | ~483 ms ~486 ms ~494 ms | |
#246 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 105 tok/s 79 tok/s 49 tok/s | ~483 ms ~486 ms ~494 ms | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 341 tok/s 322 tok/s 287 tok/s | ~32 ms ~33 ms ~33 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 323 tok/s 296 tok/s 250 tok/s | ~49 ms ~50 ms ~50 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 323 tok/s 296 tok/s 250 tok/s | ~49 ms ~50 ms ~50 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 320 tok/s 305 tok/s 274 tok/s | ~33 ms ~33 ms ~33 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 320 tok/s 305 tok/s 274 tok/s | ~33 ms ~33 ms ~33 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 315 tok/s 285 tok/s 234 tok/s | ~58 ms ~59 ms ~59 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 314 tok/s 284 tok/s 233 tok/s | ~59 ms ~59 ms ~60 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 314 tok/s 284 tok/s 233 tok/s | ~59 ms ~59 ms ~60 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 312 tok/s 281 tok/s 230 tok/s | ~61 ms ~61 ms ~62 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 295 tok/s 258 tok/s 202 tok/s | ~82 ms ~82 ms ~83 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 295 tok/s 258 tok/s 202 tok/s | ~82 ms ~82 ms ~83 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 295 tok/s 258 tok/s 202 tok/s | ~82 ms ~82 ms ~83 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 293 tok/s 251 tok/s 191 tok/s | ~95 ms ~96 ms ~97 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 284 tok/s 245 tok/s 187 tok/s | ~95 ms ~96 ms ~97 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 284 tok/s 245 tok/s 187 tok/s | ~95 ms ~96 ms ~97 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 271 tok/s 228 tok/s 169 tok/s | ~113 ms ~114 ms ~115 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 267 tok/s 223 tok/s 164 tok/s | ~119 ms ~120 ms ~122 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 256 tok/s 210 tok/s 151 tok/s | ~136 ms ~137 ms ~139 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 256 tok/s 210 tok/s 151 tok/s | ~136 ms ~137 ms ~139 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 256 tok/s 210 tok/s 151 tok/s | ~136 ms ~137 ms ~139 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 256 tok/s 210 tok/s 151 tok/s | ~136 ms ~137 ms ~139 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 246 tok/s 199 tok/s 140 tok/s | ~153 ms ~154 ms ~156 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 246 tok/s 199 tok/s 140 tok/s | ~153 ms ~154 ms ~156 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 246 tok/s 199 tok/s 140 tok/s | ~153 ms ~154 ms ~156 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 242 tok/s 194 tok/s 135 tok/s | ~161 ms ~162 ms ~164 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 233 tok/s 184 tok/s 126 tok/s | ~178 ms ~179 ms ~181 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 233 tok/s 184 tok/s 126 tok/s | ~178 ms ~179 ms ~181 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 233 tok/s 184 tok/s 126 tok/s | ~178 ms ~179 ms ~181 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 233 tok/s 184 tok/s 126 tok/s | ~178 ms ~179 ms ~181 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 233 tok/s 184 tok/s 126 tok/s | ~178 ms ~179 ms ~181 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 233 tok/s 184 tok/s 126 tok/s | ~178 ms ~179 ms ~181 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 FP16 | 233 tok/s 184 tok/s 120 tok/s | ~199 ms ~200 ms ~220 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 233 tok/s 184 tok/s 126 tok/s | ~178 ms ~179 ms ~181 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 122 tok/s | ~185 ms ~187 ms ~189 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 225 tok/s 176 tok/s 118 tok/s | ~193 ms ~194 ms ~197 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 222 tok/s 172 tok/s 115 tok/s | ~201 ms ~202 ms ~205 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 215 tok/s 165 tok/s 109 tok/s | ~215 ms ~217 ms ~220 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 213 tok/s 163 tok/s 107 tok/s | ~220 ms ~221 ms ~225 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 213 tok/s 163 tok/s 107 tok/s | ~220 ms ~221 ms ~225 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 208 tok/s 153 tok/s 97 tok/s | ~253 ms ~255 ms ~258 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 205 tok/s 181 tok/s 140 tok/s | ~121 ms ~121 ms ~123 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 205 tok/s 181 tok/s 140 tok/s | ~121 ms ~121 ms ~123 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 205 tok/s 181 tok/s 140 tok/s | ~121 ms ~121 ms ~123 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 202 tok/s 150 tok/s 96 tok/s | ~253 ms ~255 ms ~258 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 FP16 | 202 tok/s 158 tok/s 95 tok/s | ~247 ms ~249 ms ~294 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 200 tok/s 149 tok/s 95 tok/s | ~253 ms ~255 ms ~259 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 200 tok/s 149 tok/s 95 tok/s | ~253 ms ~255 ms ~259 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 200 tok/s 149 tok/s 95 tok/s | ~253 ms ~255 ms ~259 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 200 tok/s 149 tok/s 95 tok/s | ~253 ms ~255 ms ~259 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 200 tok/s 149 tok/s 95 tok/s | ~253 ms ~255 ms ~259 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 200 tok/s 149 tok/s 95 tok/s | ~253 ms ~255 ms ~259 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 190 tok/s | ~279 ms | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 Q8 | 181 tok/s 125 tok/s | ~308 ms ~363 ms | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 Q8 | 181 tok/s 125 tok/s | ~308 ms ~363 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 177 tok/s | ~323 ms | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 177 tok/s | ~323 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 175 tok/s 125 tok/s 77 tok/s | ~329 ms ~331 ms ~336 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 175 tok/s 125 tok/s 77 tok/s | ~329 ms ~331 ms ~336 ms | |
- | Hy-Memory 30B A3B | 30B (3B active) | INT4 | 175 tok/s | ~328 ms | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 | 175 tok/s | ~328 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 175 tok/s 125 tok/s 77 tok/s | ~329 ms ~331 ms ~336 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 175 tok/s 125 tok/s 77 tok/s | ~329 ms ~331 ms ~336 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 170 tok/s 145 tok/s 106 tok/s | ~179 ms ~180 ms ~183 ms | |
- | MiniCPM-V 4.7 35B A3B | 35B (3B active) | INT4 | 165 tok/s | ~363 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 156 tok/s 108 tok/s 64 tok/s | ~405 ms ~408 ms ~414 ms | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 156 tok/s 108 tok/s 64 tok/s | ~405 ms ~408 ms ~414 ms | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 156 tok/s 108 tok/s 64 tok/s | ~405 ms ~408 ms ~414 ms | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 154 tok/s 127 tok/s 89 tok/s | ~232 ms ~234 ms ~237 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 148 tok/s 120 tok/s 83 tok/s | ~255 ms ~256 ms ~260 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 148 tok/s 120 tok/s 83 tok/s | ~255 ms ~256 ms ~260 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 132 tok/s 86 tok/s 49 tok/s | ~557 ms ~561 ms ~569 ms | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 130 tok/s 86 tok/s 50 tok/s | ~542 ms ~546 ms ~554 ms | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 130 tok/s 86 tok/s 50 tok/s | ~542 ms ~546 ms ~554 ms | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 127 tok/s 85 tok/s 48 tok/s | ~557 ms ~561 ms ~570 ms | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 127 tok/s 85 tok/s 48 tok/s | ~557 ms ~561 ms ~570 ms | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 124 tok/s 82 tok/s 47 tok/s | ~579 ms ~583 ms ~593 ms | |
- | Youtu Parsing Omni | 8B | INT4 Q8 FP16 | 119 tok/s 77 tok/s 43 tok/s | ~632 ms ~637 ms ~647 ms | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 FP16 | 116 tok/s 76 tok/s 43 tok/s | ~640 ms ~645 ms ~655 ms | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 FP16 | 116 tok/s 76 tok/s 43 tok/s | ~640 ms ~645 ms ~655 ms | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 FP16 | 108 tok/s 69 tok/s 37 tok/s | ~710 ms ~715 ms ~788 ms | |
- | LensVLM 9B | 9B | INT4 Q8 FP16 | 108 tok/s 69 tok/s 37 tok/s | ~710 ms ~715 ms ~788 ms | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 FP16 | 108 tok/s 69 tok/s 37 tok/s | ~710 ms ~715 ms ~788 ms | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 105 tok/s 79 tok/s 49 tok/s | ~483 ms ~486 ms ~494 ms | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 105 tok/s 79 tok/s 49 tok/s | ~483 ms ~486 ms ~494 ms | |
- | Falcon3-10B | 10B | INT4 Q8 FP16 | 100 tok/s 64 tok/s 34 tok/s | ~786 ms ~792 ms ~872 ms | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 Q8 | 100 tok/s 84 tok/s | ~300 ms ~327 ms | |
- | Mochi 1 Preview | 10B | INT4 Q8 FP16 | 100 tok/s 64 tok/s 34 tok/s | ~786 ms ~792 ms ~872 ms | |
- | Falcon2-11B | 11B | INT4 Q8 FP16 | 97 tok/s 60 tok/s 30 tok/s | ~862 ms ~868 ms ~1.0s | |
- | Hunyuan Lite | 7B | INT4 Q8 FP16 | 96 tok/s 70 tok/s 43 tok/s | ~559 ms ~563 ms ~572 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 FP16 | 96 tok/s 70 tok/s 43 tok/s | ~559 ms ~563 ms ~572 ms | |
- | SEA-LION-7B | 7.1B | INT4 Q8 FP16 | 95 tok/s 70 tok/s 43 tok/s | ~567 ms ~571 ms ~580 ms | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 FP16 | 95 tok/s 70 tok/s 43 tok/s | ~567 ms ~571 ms ~580 ms | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 FP16 | 88 tok/s 55 tok/s 27 tok/s | ~932 ms ~939 ms ~1.1s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 FP16 | 88 tok/s 55 tok/s 27 tok/s | ~932 ms ~939 ms ~1.1s | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 FP16 | 88 tok/s 55 tok/s 27 tok/s | ~932 ms ~939 ms ~1.1s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 FP16 | 88 tok/s 55 tok/s 27 tok/s | ~932 ms ~939 ms ~1.1s | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 FP16 | 88 tok/s 55 tok/s 27 tok/s | ~932 ms ~939 ms ~1.1s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 FP16 | 88 tok/s 64 tok/s 37 tok/s | ~635 ms ~640 ms ~705 ms | |
- | Typhoon-2-8B | 8B | INT4 Q8 FP16 | 88 tok/s 64 tok/s 37 tok/s | ~635 ms ~640 ms ~705 ms | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 82 tok/s 51 tok/s | ~1.0s ~1.0s | |
- | GLM-4-9B | 9B | INT4 Q8 FP16 | 81 tok/s 58 tok/s 33 tok/s | ~713 ms ~718 ms ~791 ms | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 FP16 | 81 tok/s 58 tok/s 33 tok/s | ~713 ms ~718 ms ~791 ms | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 FP16 | 81 tok/s 58 tok/s 33 tok/s | ~713 ms ~718 ms ~791 ms | |
- | Yi-9B | 9B | INT4 Q8 FP16 | 81 tok/s 58 tok/s 33 tok/s | ~713 ms ~718 ms ~791 ms | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 FP16 | 80 tok/s 57 tok/s 33 tok/s | ~728 ms ~733 ms ~807 ms | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 FP16 | 80 tok/s 57 tok/s 33 tok/s | ~728 ms ~733 ms ~807 ms | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 78 tok/s 48 tok/s | ~1.1s ~1.1s | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 78 tok/s 48 tok/s | ~1.1s ~1.1s | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 78 tok/s 48 tok/s | ~1.1s ~1.1s | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 74 tok/s 45 tok/s | ~1.2s ~1.2s | |
- | GreenMind-14B-R1 | 14B | INT4 Q8 | 59 tok/s 40 tok/s | ~1.1s ~1.1s | |
- | Arete 27B | 27B | INT4 | 45 tok/s | ~2.1s | |
- | AREX-2 | 27B | INT4 | 45 tok/s | ~2.1s | |
- | PPLX Decider v1 27B | 27B | INT4 | 45 tok/s | ~2.1s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 45 tok/s | ~2.1s | |
- | Agnes 3.0 Flash | 33B | INT4 | 38 tok/s | ~2.5s | |
- | Falcon-40B | 40B | INT4 | 31 tok/s | ~3.3s | |
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 3090 (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 936.2 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 208 tok/s on an 8B Q4 model and 25 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning