NVIDIA RTX 5070 (12GB)
The NVIDIA RTX 5070 (12GB) features 12 GB of dedicated VRAM and 672 GB/s memory bandwidth, supporting CUDA and TensorRT-LLM runtimes for full-precision and quantized inference.
Memory
12 GB
Usable Memory Ceiling
12 GB
Bandwidth
672 GB/s
Max Inference Class
14B Models (Q4)
TDP
220W
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 5070 (12GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA RTX 5070 (12GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#112 | Phi-4 Reasoning Plus | 14B | INT4 | 40 tok/s | ~1.5s | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 | 84 tok/s 50 tok/s | ~820 ms ~898 ms | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 | 101 tok/s 65 tok/s | ~643 ms ~649 ms | |
#135 | Gemma 4 12B | 11.95B | INT4 | 47 tok/s | ~1.2s | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~380 ms ~383 ms ~390 ms | |
#144 | GLM-4V | 9B | INT4 | 62 tok/s | ~825 ms | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 29 tok/s 17 tok/s 9 tok/s | ~2.6s ~2.6s ~2.9s | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 | 92 tok/s 55 tok/s | ~731 ms ~800 ms | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 | 92 tok/s 55 tok/s | ~731 ms ~800 ms | |
#166 | Phi-4 | 14B | INT4 | 59 tok/s | ~1.3s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 | 74 tok/s 51 tok/s | ~647 ms ~707 ms | |
#179 | DeepSeek-R1 14B | 14B | INT4 | 61 tok/s | ~1.3s | |
#183 | Ministral 3 14B | 14B | INT4 | 40 tok/s | ~1.5s | |
#186 | Gemma 3 12B | 12B | INT4 | 67 tok/s | ~1.1s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 | 68 tok/s 43 tok/s | ~735 ms ~869 ms | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~205 ms ~206 ms ~210 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~205 ms ~206 ms ~210 ms | |
#194 | Qwen2.5-14B | 14B | INT4 | 59 tok/s | ~1.3s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 125 tok/s 83 tok/s 43 tok/s | ~476 ms ~480 ms ~573 ms | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 | 94 tok/s 59 tok/s | ~731 ms ~737 ms | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~380 ms ~383 ms ~390 ms | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 120 tok/s 95 tok/s 63 tok/s | ~294 ms ~296 ms ~302 ms | |
#207 | Gemma 2 9B | 9B | INT4 Q8 | 84 tok/s 50 tok/s | ~820 ms ~898 ms | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 278 tok/s 237 tok/s 178 tok/s | ~87 ms ~88 ms ~89 ms | |
#209 | Qwen3-14B | 14B | INT4 | 59 tok/s | ~1.3s | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~380 ms ~383 ms ~390 ms | |
#211 | Qwen3-8B | 8B | INT4 Q8 | 92 tok/s 55 tok/s | ~731 ms ~800 ms | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 | 104 tok/s 66 tok/s | ~643 ms ~649 ms | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 217 tok/s 168 tok/s 112 tok/s | ~176 ms ~177 ms ~180 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 | 92 tok/s 55 tok/s | ~731 ms ~800 ms | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 311 tok/s 293 tok/s 257 tok/s | ~34 ms ~34 ms ~34 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 298 tok/s 261 tok/s 205 tok/s | ~66 ms ~67 ms ~68 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 | 92 tok/s 55 tok/s | ~731 ms ~800 ms | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 149 tok/s 103 tok/s 61 tok/s | ~362 ms ~365 ms ~372 ms | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 | 101 tok/s 65 tok/s | ~643 ms ~649 ms | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 | 92 tok/s 55 tok/s | ~731 ms ~800 ms | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 228 tok/s 180 tok/s 122 tok/s | ~156 ms ~158 ms ~160 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~292 ms ~294 ms ~299 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 149 tok/s 103 tok/s 61 tok/s | ~362 ms ~365 ms ~372 ms | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 | 119 tok/s 103 tok/s | ~221 ms ~223 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 | 98 tok/s 63 tok/s | ~669 ms ~675 ms | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 260 tok/s 216 tok/s 157 tok/s | ~109 ms ~110 ms ~112 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~205 ms ~206 ms ~210 ms | |
#233 | Phi-3-medium | 14B | INT4 | 59 tok/s | ~1.3s | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 | 74 tok/s 51 tok/s | ~647 ms ~707 ms | |
#236 | Qwen2-7B | 7B | INT4 Q8 | 101 tok/s 65 tok/s | ~643 ms ~649 ms | |
#237 | Phi-3-small | 7B | INT4 Q8 | 101 tok/s 65 tok/s | ~643 ms ~649 ms | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 260 tok/s 216 tok/s 157 tok/s | ~109 ms ~110 ms ~112 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 | 98 tok/s 63 tok/s | ~669 ms ~675 ms | |
#241 | Gemma 1 7B | 7B | INT4 Q8 | 74 tok/s 51 tok/s | ~647 ms ~707 ms | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 214 tok/s 159 tok/s 102 tok/s | ~204 ms ~206 ms ~209 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 | 82 tok/s 60 tok/s | ~559 ms ~563 ms | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 | 82 tok/s 60 tok/s | ~559 ms ~563 ms | |
#245 | ChatGLM-6B | 6B | INT4 Q8 | 82 tok/s 60 tok/s | ~559 ms ~563 ms | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 331 tok/s 307 tok/s 264 tok/s | ~36 ms ~37 ms ~37 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 308 tok/s 275 tok/s 221 tok/s | ~56 ms ~56 ms ~57 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 308 tok/s 275 tok/s 221 tok/s | ~56 ms ~56 ms ~57 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 304 tok/s 285 tok/s 248 tok/s | ~37 ms ~37 ms ~37 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 304 tok/s 285 tok/s 248 tok/s | ~37 ms ~37 ms ~37 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 298 tok/s 261 tok/s 205 tok/s | ~66 ms ~67 ms ~68 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 297 tok/s 260 tok/s 203 tok/s | ~67 ms ~68 ms ~69 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 297 tok/s 260 tok/s 203 tok/s | ~67 ms ~68 ms ~69 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 294 tok/s 257 tok/s 200 tok/s | ~69 ms ~70 ms ~71 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 273 tok/s 230 tok/s 171 tok/s | ~94 ms ~94 ms ~96 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 273 tok/s 230 tok/s 171 tok/s | ~94 ms ~94 ms ~96 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 273 tok/s 230 tok/s 171 tok/s | ~94 ms ~94 ms ~96 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 270 tok/s 223 tok/s 160 tok/s | ~109 ms ~110 ms ~111 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 260 tok/s 216 tok/s 157 tok/s | ~109 ms ~110 ms ~112 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 260 tok/s 216 tok/s 157 tok/s | ~109 ms ~110 ms ~112 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 245 tok/s 199 tok/s 139 tok/s | ~130 ms ~131 ms ~133 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 240 tok/s 193 tok/s 134 tok/s | ~137 ms ~138 ms ~140 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 228 tok/s 180 tok/s 122 tok/s | ~156 ms ~158 ms ~160 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 228 tok/s 180 tok/s 122 tok/s | ~156 ms ~158 ms ~160 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 228 tok/s 180 tok/s 122 tok/s | ~156 ms ~158 ms ~160 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 228 tok/s 180 tok/s 122 tok/s | ~156 ms ~158 ms ~160 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 217 tok/s 168 tok/s 112 tok/s | ~176 ms ~177 ms ~180 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 217 tok/s 168 tok/s 112 tok/s | ~176 ms ~177 ms ~180 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 217 tok/s 168 tok/s 112 tok/s | ~176 ms ~177 ms ~180 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 213 tok/s 164 tok/s 108 tok/s | ~185 ms ~186 ms ~189 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~205 ms ~206 ms ~210 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~205 ms ~206 ms ~210 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~205 ms ~206 ms ~210 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~205 ms ~206 ms ~210 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~205 ms ~206 ms ~210 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~205 ms ~206 ms ~210 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 | 203 tok/s 146 tok/s | ~229 ms ~250 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 203 tok/s 154 tok/s 100 tok/s | ~205 ms ~206 ms ~210 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 199 tok/s 150 tok/s 97 tok/s | ~213 ms ~215 ms ~219 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 195 tok/s 146 tok/s 93 tok/s | ~222 ms ~224 ms ~228 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 191 tok/s 142 tok/s 90 tok/s | ~232 ms ~233 ms ~237 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 185 tok/s 135 tok/s 85 tok/s | ~248 ms ~250 ms ~255 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 183 tok/s 133 tok/s 84 tok/s | ~253 ms ~255 ms ~260 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 183 tok/s 133 tok/s 84 tok/s | ~253 ms ~255 ms ~260 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 177 tok/s 125 tok/s 75 tok/s | ~291 ms ~294 ms ~299 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 175 tok/s 151 tok/s 112 tok/s | ~139 ms ~139 ms ~142 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 175 tok/s 151 tok/s 112 tok/s | ~139 ms ~139 ms ~142 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 175 tok/s 151 tok/s 112 tok/s | ~139 ms ~139 ms ~142 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 | 172 tok/s | ~285 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 171 tok/s 122 tok/s 74 tok/s | ~292 ms ~294 ms ~299 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~292 ms ~294 ms ~299 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~292 ms ~294 ms ~299 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~292 ms ~294 ms ~299 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~292 ms ~294 ms ~299 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~292 ms ~294 ms ~299 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 169 tok/s 121 tok/s 74 tok/s | ~292 ms ~294 ms ~299 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~380 ms ~383 ms ~390 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~380 ms ~383 ms ~390 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~380 ms ~383 ms ~390 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 145 tok/s 99 tok/s 59 tok/s | ~380 ms ~383 ms ~390 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 140 tok/s 117 tok/s 83 tok/s | ~207 ms ~208 ms ~212 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 127 tok/s 84 tok/s 46 tok/s | ~468 ms ~472 ms ~521 ms | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 127 tok/s 84 tok/s 46 tok/s | ~468 ms ~472 ms ~521 ms | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 127 tok/s 84 tok/s 46 tok/s | ~468 ms ~472 ms ~521 ms | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 125 tok/s 101 tok/s 68 tok/s | ~268 ms ~270 ms ~275 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 120 tok/s 95 tok/s 63 tok/s | ~294 ms ~296 ms ~302 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 120 tok/s 95 tok/s 63 tok/s | ~294 ms ~296 ms ~302 ms | |
- | Falcon-7B | 7B | INT4 Q8 | 105 tok/s 66 tok/s | ~643 ms ~649 ms | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 | 103 tok/s 66 tok/s | ~626 ms ~631 ms | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 | 103 tok/s 66 tok/s | ~626 ms ~631 ms | |
- | Falcon3-7B | 7B | INT4 Q8 | 101 tok/s 65 tok/s | ~643 ms ~649 ms | |
- | Hy-MT2 7B | 7B | INT4 Q8 | 101 tok/s 65 tok/s | ~643 ms ~649 ms | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 | 98 tok/s 63 tok/s | ~669 ms ~675 ms | |
- | Youtu Parsing Omni | 8B | INT4 Q8 | 94 tok/s 59 tok/s | ~731 ms ~737 ms | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 | 91 tok/s 55 tok/s | ~740 ms ~810 ms | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 | 91 tok/s 55 tok/s | ~740 ms ~810 ms | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 | 84 tok/s 50 tok/s | ~820 ms ~898 ms | |
- | LensVLM 9B | 9B | INT4 Q8 | 84 tok/s 50 tok/s | ~820 ms ~898 ms | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 | 84 tok/s 50 tok/s | ~820 ms ~898 ms | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 | 82 tok/s 60 tok/s | ~559 ms ~563 ms | |
- | Yi-6B | 6B | INT4 Q8 | 82 tok/s 60 tok/s | ~559 ms ~563 ms | |
- | Falcon3-10B | 10B | INT4 Q8 | 78 tok/s 43 tok/s | ~908 ms ~1.1s | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 78 tok/s 43 tok/s | ~908 ms ~1.1s | |
- | Falcon2-11B | 11B | INT4 Q8 | 75 tok/s 41 tok/s | ~996 ms ~1.2s | |
- | Hunyuan Lite | 7B | INT4 Q8 | 74 tok/s 51 tok/s | ~647 ms ~707 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 | 74 tok/s 51 tok/s | ~647 ms ~707 ms | |
- | SEA-LION-7B | 7.1B | INT4 Q8 | 74 tok/s 50 tok/s | ~656 ms ~717 ms | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 | 74 tok/s 50 tok/s | ~656 ms ~717 ms | |
- | FLUX.1 Canny Dev | 11.9B | INT4 | 68 tok/s | ~1.1s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 | 68 tok/s | ~1.1s | |
- | FLUX.1 Dev | 11.9B | INT4 | 68 tok/s | ~1.1s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 | 68 tok/s | ~1.1s | |
- | FLUX.1 Schnell | 11.9B | INT4 | 68 tok/s | ~1.1s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 | 68 tok/s 43 tok/s | ~735 ms ~869 ms | |
- | Typhoon-2-8B | 8B | INT4 Q8 | 68 tok/s 43 tok/s | ~735 ms ~869 ms | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 | 63 tok/s | ~1.2s | |
- | GLM-4-9B | 9B | INT4 | 62 tok/s | ~825 ms | |
- | GLM-4-9B-Chat | 9B | INT4 | 62 tok/s | ~825 ms | |
- | GLM-4-9B-Chat-1M | 9B | INT4 | 62 tok/s | ~825 ms | |
- | Yi-9B | 9B | INT4 | 62 tok/s | ~825 ms | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 | 61 tok/s | ~842 ms | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 | 61 tok/s | ~842 ms | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 | 59 tok/s | ~1.3s | |
- | Wan 2.1 T2V 14B | 14B | INT4 | 59 tok/s | ~1.3s | |
- | Wan 2.2 T2V A14B | 14B | INT4 | 59 tok/s | ~1.3s | |
- | FLUX.2 Dev | 15B | INT4 | 56 tok/s | ~1.3s | |
- | GreenMind-14B-R1 | 14B | INT4 | 40 tok/s | ~1.5s | |
Inference Capacity
Maximum model parameter class runnable by weight precision.
Context:
4-bit
14B Models
8-bit
8B Models
16-bit
3B Models
Fine-Tuning Capacity
Hardware capacity for local training and adapter fine-tuning.
Context Length:
QLoRA
14B Models
LoRA
8B Models
Full Parameter Training
1B Models
Workload Recommendations
Guidance for optimal precision and operational ceilings on NVIDIA RTX 5070 (12GB).
Inference Sweet Spot
Optimal for 8B models across extended context (32k+). 14B models fit comfortably at Q4 precision with standard 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