NVIDIA RTX 4080 SUPER (16GB)
The NVIDIA RTX 4080 SUPER (16GB) features 16 GB of dedicated VRAM and 736 GB/s memory bandwidth, supporting CUDA and TensorRT-LLM runtimes for full-precision and quantized inference.
Memory
16 GB
Usable Memory Ceiling
16 GB
Bandwidth
736.3 GB/s
Max Inference Class
14B Models (Q4)
TDP
320W
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 4080 SUPER (16GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA RTX 4080 SUPER (16GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#48 | Qwen 3.8 27B | 27B | INT4 | 33 tok/s | ~1.7s | |
#93 | Qwen3.5-27B | 27B | INT4 | 33 tok/s | ~1.7s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 | 3 tok/s | ~17.0s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 | 48 tok/s | ~763 ms | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 134 tok/s | ~284 ms | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 | 90 tok/s 57 tok/s | ~493 ms ~499 ms | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 108 tok/s 70 tok/s 35 tok/s | ~387 ms ~392 ms ~471 ms | |
#135 | Gemma 4 12B | 11.95B | INT4 Q8 | 54 tok/s 34 tok/s | ~654 ms ~775 ms | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 153 tok/s 106 tok/s 63 tok/s | ~230 ms ~233 ms ~239 ms | |
#143 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 66 tok/s | ~295 ms | |
#144 | GLM-4V | 9B | INT4 Q8 | 67 tok/s 45 tok/s | ~497 ms ~545 ms | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 32 tok/s 19 tok/s 10 tok/s | ~1.5s ~1.6s ~1.6s | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 | 99 tok/s 63 tok/s | ~440 ms ~445 ms | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 | 99 tok/s 63 tok/s | ~440 ms ~445 ms | |
#166 | Phi-4 | 14B | INT4 Q8 | 64 tok/s 35 tok/s | ~757 ms ~899 ms | |
#167 | Gemma 3 27B | 27B | INT4 | 33 tok/s | ~1.7s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 | 80 tok/s 58 tok/s | ~390 ms ~395 ms | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 66 tok/s 35 tok/s | ~757 ms ~899 ms | |
#183 | Ministral 3 14B | 14B | INT4 | 48 tok/s | ~763 ms | |
#186 | Gemma 3 12B | 12B | INT4 Q8 | 72 tok/s 42 tok/s | ~652 ms ~716 ms | |
#188 | Mistral-Small-2501 | 24B | INT4 | 39 tok/s | ~1.4s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 | 73 tok/s 52 tok/s | ~443 ms ~449 ms | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
#193 | Gemma 2 27B | 27B | INT4 | 33 tok/s | ~1.7s | |
#194 | Qwen2.5-14B | 14B | INT4 Q8 | 64 tok/s 35 tok/s | ~757 ms ~899 ms | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 133 tok/s 89 tok/s 52 tok/s | ~287 ms ~291 ms ~299 ms | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 | 101 tok/s 64 tok/s | ~439 ms ~445 ms | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 153 tok/s 106 tok/s 63 tok/s | ~230 ms ~233 ms ~239 ms | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 127 tok/s 101 tok/s 68 tok/s | ~180 ms ~182 ms ~186 ms | |
#207 | Gemma 2 9B | 9B | INT4 Q8 | 90 tok/s 57 tok/s | ~493 ms ~499 ms | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 284 tok/s 244 tok/s 186 tok/s | ~55 ms ~56 ms ~57 ms | |
#209 | Qwen3-14B | 14B | INT4 Q8 | 64 tok/s 35 tok/s | ~757 ms ~899 ms | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 153 tok/s 106 tok/s 63 tok/s | ~230 ms ~233 ms ~239 ms | |
#211 | Qwen3-8B | 8B | INT4 Q8 | 99 tok/s 63 tok/s | ~440 ms ~445 ms | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 111 tok/s 71 tok/s 38 tok/s | ~387 ms ~392 ms ~437 ms | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 226 tok/s 177 tok/s 119 tok/s | ~108 ms ~109 ms ~112 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 | 99 tok/s 63 tok/s | ~440 ms ~445 ms | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 315 tok/s 299 tok/s 264 tok/s | ~23 ms ~23 ms ~24 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 303 tok/s 268 tok/s 213 tok/s | ~43 ms ~43 ms ~44 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 | 99 tok/s 63 tok/s | ~440 ms ~445 ms | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 157 tok/s 110 tok/s 66 tok/s | ~219 ms ~222 ms ~228 ms | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 108 tok/s 70 tok/s 35 tok/s | ~387 ms ~392 ms ~471 ms | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 | 99 tok/s 63 tok/s | ~440 ms ~445 ms | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 236 tok/s 188 tok/s 130 tok/s | ~96 ms ~98 ms ~100 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 178 tok/s 128 tok/s 79 tok/s | ~177 ms ~179 ms ~184 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 157 tok/s 110 tok/s 66 tok/s | ~219 ms ~222 ms ~228 ms | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 127 tok/s 110 tok/s 78 tok/s | ~136 ms ~137 ms ~152 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 105 tok/s 68 tok/s 34 tok/s | ~403 ms ~408 ms ~490 ms | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 267 tok/s 224 tok/s 165 tok/s | ~68 ms ~69 ms ~70 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
#233 | Phi-3-medium | 14B | INT4 Q8 | 64 tok/s 35 tok/s | ~757 ms ~899 ms | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 | 80 tok/s 58 tok/s | ~390 ms ~395 ms | |
#236 | Qwen2-7B | 7B | INT4 Q8 FP16 | 108 tok/s 70 tok/s 35 tok/s | ~387 ms ~392 ms ~471 ms | |
#237 | Phi-3-small | 7B | INT4 Q8 FP16 | 108 tok/s 70 tok/s 35 tok/s | ~387 ms ~392 ms ~471 ms | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 267 tok/s 224 tok/s 165 tok/s | ~68 ms ~69 ms ~70 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 105 tok/s 68 tok/s 34 tok/s | ~403 ms ~408 ms ~490 ms | |
#241 | Gemma 1 7B | 7B | INT4 Q8 | 80 tok/s 58 tok/s | ~390 ms ~395 ms | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 222 tok/s 168 tok/s 109 tok/s | ~125 ms ~126 ms ~130 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 88 tok/s 65 tok/s 38 tok/s | ~338 ms ~342 ms ~380 ms | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 88 tok/s 65 tok/s 38 tok/s | ~338 ms ~342 ms ~380 ms | |
#245 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 88 tok/s 65 tok/s 38 tok/s | ~338 ms ~342 ms ~380 ms | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 334 tok/s 311 tok/s 271 tok/s | ~25 ms ~25 ms ~26 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 313 tok/s 281 tok/s 230 tok/s | ~37 ms ~37 ms ~38 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 313 tok/s 281 tok/s 230 tok/s | ~37 ms ~37 ms ~38 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 309 tok/s 291 tok/s 256 tok/s | ~25 ms ~25 ms ~26 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 309 tok/s 291 tok/s 256 tok/s | ~25 ms ~25 ms ~26 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 303 tok/s 268 tok/s 213 tok/s | ~43 ms ~43 ms ~44 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 302 tok/s 267 tok/s 212 tok/s | ~43 ms ~44 ms ~45 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 302 tok/s 267 tok/s 212 tok/s | ~43 ms ~44 ms ~45 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 300 tok/s 264 tok/s 209 tok/s | ~45 ms ~45 ms ~46 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 279 tok/s 238 tok/s 179 tok/s | ~59 ms ~60 ms ~61 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 279 tok/s 238 tok/s 179 tok/s | ~59 ms ~60 ms ~61 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 279 tok/s 238 tok/s 179 tok/s | ~59 ms ~60 ms ~61 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 277 tok/s 231 tok/s 169 tok/s | ~68 ms ~69 ms ~70 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 267 tok/s 224 tok/s 165 tok/s | ~68 ms ~69 ms ~70 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 267 tok/s 224 tok/s 165 tok/s | ~68 ms ~69 ms ~70 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 253 tok/s 207 tok/s 147 tok/s | ~81 ms ~81 ms ~83 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 248 tok/s 201 tok/s 142 tok/s | ~85 ms ~86 ms ~88 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 236 tok/s 188 tok/s 130 tok/s | ~96 ms ~98 ms ~100 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 236 tok/s 188 tok/s 130 tok/s | ~96 ms ~98 ms ~100 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 236 tok/s 188 tok/s 130 tok/s | ~96 ms ~98 ms ~100 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 236 tok/s 188 tok/s 130 tok/s | ~96 ms ~98 ms ~100 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 226 tok/s 177 tok/s 119 tok/s | ~108 ms ~109 ms ~112 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 226 tok/s 177 tok/s 119 tok/s | ~108 ms ~109 ms ~112 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 226 tok/s 177 tok/s 119 tok/s | ~108 ms ~109 ms ~112 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 221 tok/s 172 tok/s 115 tok/s | ~113 ms ~115 ms ~118 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 | 212 tok/s 162 tok/s | ~140 ms ~141 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 211 tok/s 162 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 208 tok/s 158 tok/s 103 tok/s | ~130 ms ~132 ms ~135 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 204 tok/s 154 tok/s 100 tok/s | ~136 ms ~137 ms ~141 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 200 tok/s 150 tok/s 97 tok/s | ~141 ms ~143 ms ~147 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 193 tok/s 143 tok/s 91 tok/s | ~151 ms ~153 ms ~157 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 191 tok/s 141 tok/s 90 tok/s | ~154 ms ~156 ms ~160 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 191 tok/s 141 tok/s 90 tok/s | ~154 ms ~156 ms ~160 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 186 tok/s 132 tok/s 81 tok/s | ~177 ms ~179 ms ~184 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 183 tok/s 159 tok/s 120 tok/s | ~86 ms ~87 ms ~89 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 183 tok/s 159 tok/s 120 tok/s | ~86 ms ~87 ms ~89 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 183 tok/s 159 tok/s 120 tok/s | ~86 ms ~87 ms ~89 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 180 tok/s 129 tok/s 80 tok/s | ~177 ms ~179 ms ~184 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 | 180 tok/s 130 tok/s | ~173 ms ~189 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 178 tok/s 128 tok/s 79 tok/s | ~177 ms ~179 ms ~184 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 178 tok/s 128 tok/s 79 tok/s | ~177 ms ~179 ms ~184 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 178 tok/s 128 tok/s 79 tok/s | ~177 ms ~179 ms ~184 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 178 tok/s 128 tok/s 79 tok/s | ~177 ms ~179 ms ~184 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 178 tok/s 128 tok/s 79 tok/s | ~177 ms ~179 ms ~184 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 178 tok/s 128 tok/s 79 tok/s | ~177 ms ~179 ms ~184 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 160 tok/s | ~212 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 153 tok/s 106 tok/s 63 tok/s | ~230 ms ~233 ms ~239 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 153 tok/s 106 tok/s 63 tok/s | ~230 ms ~233 ms ~239 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 153 tok/s 106 tok/s 63 tok/s | ~230 ms ~233 ms ~239 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 153 tok/s 106 tok/s 63 tok/s | ~230 ms ~233 ms ~239 ms | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 | 151 tok/s | ~233 ms | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 | 151 tok/s | ~233 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 148 tok/s 124 tok/s 89 tok/s | ~127 ms ~128 ms ~132 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 139 tok/s | ~264 ms | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 139 tok/s | ~264 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 134 tok/s 90 tok/s 53 tok/s | ~282 ms ~286 ms ~294 ms | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 134 tok/s 90 tok/s 53 tok/s | ~282 ms ~286 ms ~294 ms | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 134 tok/s 90 tok/s 53 tok/s | ~282 ms ~286 ms ~294 ms | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 133 tok/s 107 tok/s 73 tok/s | ~164 ms ~166 ms ~170 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 127 tok/s 101 tok/s 68 tok/s | ~180 ms ~182 ms ~186 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 127 tok/s 101 tok/s 68 tok/s | ~180 ms ~182 ms ~186 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 112 tok/s 71 tok/s 38 tok/s | ~387 ms ~392 ms ~437 ms | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 110 tok/s 71 tok/s 38 tok/s | ~377 ms ~382 ms ~425 ms | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 110 tok/s 71 tok/s 38 tok/s | ~377 ms ~382 ms ~425 ms | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 108 tok/s 70 tok/s 35 tok/s | ~387 ms ~392 ms ~471 ms | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 108 tok/s 70 tok/s 35 tok/s | ~387 ms ~392 ms ~471 ms | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 105 tok/s 68 tok/s 34 tok/s | ~403 ms ~408 ms ~490 ms | |
- | Youtu Parsing Omni | 8B | INT4 Q8 | 101 tok/s 64 tok/s | ~439 ms ~445 ms | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 | 98 tok/s 62 tok/s | ~445 ms ~451 ms | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 | 98 tok/s 62 tok/s | ~445 ms ~451 ms | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 | 90 tok/s 57 tok/s | ~493 ms ~499 ms | |
- | LensVLM 9B | 9B | INT4 Q8 | 90 tok/s 57 tok/s | ~493 ms ~499 ms | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 | 90 tok/s 57 tok/s | ~493 ms ~499 ms | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 88 tok/s 65 tok/s 38 tok/s | ~338 ms ~342 ms ~380 ms | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 88 tok/s 65 tok/s 38 tok/s | ~338 ms ~342 ms ~380 ms | |
- | Falcon3-10B | 10B | INT4 Q8 | 84 tok/s 52 tok/s | ~545 ms ~553 ms | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 84 tok/s 52 tok/s | ~545 ms ~553 ms | |
- | Falcon2-11B | 11B | INT4 Q8 | 81 tok/s 49 tok/s | ~598 ms ~606 ms | |
- | Hunyuan Lite | 7B | INT4 Q8 | 80 tok/s 58 tok/s | ~390 ms ~395 ms | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 | 80 tok/s | ~230 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 | 80 tok/s 58 tok/s | ~390 ms ~395 ms | |
- | SEA-LION-7B | 7.1B | INT4 Q8 | 79 tok/s 57 tok/s | ~396 ms ~401 ms | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 | 79 tok/s 57 tok/s | ~396 ms ~401 ms | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 | 73 tok/s 43 tok/s | ~647 ms ~710 ms | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 | 73 tok/s 43 tok/s | ~647 ms ~710 ms | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 | 73 tok/s 43 tok/s | ~647 ms ~710 ms | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 | 73 tok/s 43 tok/s | ~647 ms ~710 ms | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 | 73 tok/s 43 tok/s | ~647 ms ~710 ms | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 | 73 tok/s 52 tok/s | ~443 ms ~449 ms | |
- | Typhoon-2-8B | 8B | INT4 Q8 | 73 tok/s 52 tok/s | ~443 ms ~449 ms | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 68 tok/s 39 tok/s | ~705 ms ~774 ms | |
- | GLM-4-9B | 9B | INT4 Q8 | 67 tok/s 45 tok/s | ~497 ms ~545 ms | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 | 67 tok/s 45 tok/s | ~497 ms ~545 ms | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 | 67 tok/s 45 tok/s | ~497 ms ~545 ms | |
- | Yi-9B | 9B | INT4 Q8 | 67 tok/s 45 tok/s | ~497 ms ~545 ms | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 | 66 tok/s 44 tok/s | ~507 ms ~557 ms | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 | 66 tok/s 44 tok/s | ~507 ms ~557 ms | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 64 tok/s 35 tok/s | ~757 ms ~899 ms | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 64 tok/s 35 tok/s | ~757 ms ~899 ms | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 64 tok/s 35 tok/s | ~757 ms ~899 ms | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 61 tok/s 33 tok/s | ~809 ms ~960 ms | |
- | GreenMind-14B-R1 | 14B | INT4 | 48 tok/s | ~763 ms | |
- | Arete 27B | 27B | INT4 | 33 tok/s | ~1.7s | |
- | AREX-2 | 27B | INT4 | 33 tok/s | ~1.7s | |
- | PPLX Decider v1 27B | 27B | INT4 | 33 tok/s | ~1.7s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 33 tok/s | ~1.7s | |
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 4080 SUPER (16GB).
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 736.3 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 164 tok/s on an 8B Q4 model and 19 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning