NVIDIA RTX 4000 Ada Generation (20GB)
The NVIDIA RTX 4000 Ada Generation (20GB) features 20 GB of dedicated VRAM and 360 GB/s memory bandwidth, supporting CUDA and TensorRT-LLM runtimes for full-precision and quantized inference.
Memory
20 GB
Usable Memory Ceiling
20 GB
Bandwidth
360 GB/s
Max Inference Class
14B Models (Q4)
TDP
130W
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 4000 Ada Generation (20GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA RTX 4000 Ada Generation (20GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#48 | Qwen 3.8 27B | 27B | INT4 | 19 tok/s | ~2.8s | |
#83 | K2 Horizon MoVA 36B A4B | 36B (4B active) | INT4 | 72 tok/s | ~645 ms | |
#93 | Qwen3.5-27B | 27B | INT4 | 19 tok/s | ~2.8s | |
#105 | Sarvam-30B | 32B (2.4B active) | INT4 | 100 tok/s | ~417 ms | |
#106 | Qwen3.6 35B A3B | 35B (3B active) | INT4 | 84 tok/s | ~525 ms | |
#110 | Muse Glimmer 30B | 30B | INT4 | 16 tok/s | ~3.4s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 | 2 tok/s | ~30.4s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 Q8 | 25 tok/s 16 tok/s | ~1.5s ~1.6s | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 86 tok/s | ~503 ms | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 FP16 | 50 tok/s 30 tok/s 14 tok/s | ~952 ms ~966 ms ~1.2s | |
#126 | Qwen3.5-35B-A3B | 35B (3B active) | INT4 | 84 tok/s | ~525 ms | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 62 tok/s 38 tok/s 20 tok/s | ~747 ms ~757 ms ~780 ms | |
#135 | Gemma 4 12B | 11.95B | INT4 Q8 | 28 tok/s 18 tok/s | ~1.3s ~1.4s | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 95 tok/s 61 tok/s 34 tok/s | ~440 ms ~446 ms ~459 ms | |
#143 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 38 tok/s | ~525 ms | |
#144 | GLM-4V | 9B | INT4 Q8 | 36 tok/s 25 tok/s | ~960 ms ~973 ms | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 16 tok/s 9 tok/s 5 tok/s | ~3.0s ~3.0s ~3.1s | |
#153 | Qwen3-30B-A3B | 30B (3B active) | INT4 | 90 tok/s | ~477 ms | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 FP16 | 56 tok/s 34 tok/s 17 tok/s | ~848 ms ~860 ms ~961 ms | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 FP16 | 56 tok/s 34 tok/s 17 tok/s | ~848 ms ~860 ms ~961 ms | |
#166 | Phi-4 | 14B | INT4 Q8 | 34 tok/s 20 tok/s | ~1.5s ~1.5s | |
#167 | Gemma 3 27B | 27B | INT4 | 19 tok/s | ~2.8s | |
#170 | DeepSeek-R1 32B | 32B | INT4 | 16 tok/s | ~3.6s | |
#171 | Qwen3-32B | 32B | INT4 | 15 tok/s | ~3.6s | |
#175 | Magistral Small | 24B | INT4 | 15 tok/s | ~2.7s | |
#177 | Qwen2.5-32B | 32B | INT4 | 15 tok/s | ~3.6s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 FP16 | 44 tok/s 31 tok/s 17 tok/s | ~753 ms ~763 ms ~852 ms | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 35 tok/s 20 tok/s | ~1.5s ~1.5s | |
#183 | Ministral 3 14B | 14B | INT4 Q8 | 25 tok/s 16 tok/s | ~1.5s ~1.6s | |
#186 | Gemma 3 12B | 12B | INT4 Q8 | 39 tok/s 23 tok/s | ~1.3s ~1.3s | |
#188 | Mistral-Small-2501 | 24B | INT4 | 21 tok/s | ~2.5s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 FP16 | 40 tok/s 27 tok/s 14 tok/s | ~856 ms ~867 ms ~1.0s | |
#190 | Gemma 4 31B | 30.7B | INT4 | 16 tok/s | ~3.4s | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 146 tok/s 102 tok/s 61 tok/s | ~237 ms ~240 ms ~246 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 146 tok/s 102 tok/s 61 tok/s | ~237 ms ~240 ms ~246 ms | |
#193 | Gemma 2 27B | 27B | INT4 | 19 tok/s | ~2.8s | |
#194 | Qwen2.5-14B | 14B | INT4 Q8 | 34 tok/s 20 tok/s | ~1.5s ~1.5s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 80 tok/s 50 tok/s 27 tok/s | ~552 ms ~560 ms ~577 ms | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 FP16 | 57 tok/s 34 tok/s 17 tok/s | ~848 ms ~860 ms ~960 ms | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 95 tok/s 61 tok/s 34 tok/s | ~440 ms ~446 ms ~459 ms | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 75 tok/s 58 tok/s 37 tok/s | ~343 ms ~347 ms ~356 ms | |
#207 | Gemma 2 9B | 9B | INT4 Q8 FP16 | 50 tok/s 30 tok/s 14 tok/s | ~952 ms ~966 ms ~1.2s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 229 tok/s 180 tok/s 123 tok/s | ~100 ms ~101 ms ~104 ms | |
#209 | Qwen3-14B | 14B | INT4 Q8 | 34 tok/s 20 tok/s | ~1.5s ~1.5s | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 95 tok/s 61 tok/s 34 tok/s | ~440 ms ~446 ms ~459 ms | |
#211 | Qwen3-8B | 8B | INT4 Q8 FP16 | 56 tok/s 34 tok/s 17 tok/s | ~848 ms ~860 ms ~961 ms | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 64 tok/s 38 tok/s 20 tok/s | ~746 ms ~757 ms ~779 ms | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 160 tok/s 114 tok/s 70 tok/s | ~203 ms ~206 ms ~211 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 FP16 | 56 tok/s 34 tok/s 17 tok/s | ~848 ms ~860 ms ~961 ms | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 273 tok/s 248 tok/s 204 tok/s | ~38 ms ~38 ms ~39 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 254 tok/s 208 tok/s 148 tok/s | ~76 ms ~77 ms ~79 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 FP16 | 56 tok/s 34 tok/s 17 tok/s | ~848 ms ~860 ms ~961 ms | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 98 tok/s 63 tok/s 35 tok/s | ~420 ms ~425 ms ~438 ms | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 62 tok/s 38 tok/s 20 tok/s | ~747 ms ~757 ms ~780 ms | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 FP16 | 56 tok/s 34 tok/s 17 tok/s | ~848 ms ~860 ms ~961 ms | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 171 tok/s 124 tok/s 77 tok/s | ~181 ms ~183 ms ~188 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 115 tok/s 76 tok/s 44 tok/s | ~338 ms ~342 ms ~352 ms | |
#227 | Nemotron 3.5 Lightning 30B A3B | 30B (3B active) | INT4 | 90 tok/s | ~477 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 98 tok/s 63 tok/s 35 tok/s | ~420 ms ~425 ms ~438 ms | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 75 tok/s 64 tok/s 45 tok/s | ~258 ms ~261 ms ~267 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 60 tok/s 36 tok/s 19 tok/s | ~777 ms ~787 ms ~811 ms | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 207 tok/s 159 tok/s 105 tok/s | ~125 ms ~127 ms ~130 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 146 tok/s 102 tok/s 61 tok/s | ~237 ms ~240 ms ~246 ms | |
#233 | Phi-3-medium | 14B | INT4 Q8 | 34 tok/s 20 tok/s | ~1.5s ~1.5s | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 FP16 | 44 tok/s 31 tok/s 17 tok/s | ~753 ms ~763 ms ~852 ms | |
#236 | Qwen2-7B | 7B | INT4 Q8 FP16 | 62 tok/s 38 tok/s 20 tok/s | ~747 ms ~757 ms ~780 ms | |
#237 | Phi-3-small | 7B | INT4 Q8 FP16 | 62 tok/s 38 tok/s 20 tok/s | ~747 ms ~757 ms ~780 ms | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 207 tok/s 159 tok/s 105 tok/s | ~125 ms ~127 ms ~130 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 60 tok/s 36 tok/s 19 tok/s | ~777 ms ~787 ms ~811 ms | |
#241 | Gemma 1 7B | 7B | INT4 Q8 FP16 | 44 tok/s 31 tok/s 17 tok/s | ~753 ms ~763 ms ~852 ms | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 156 tok/s 107 tok/s 63 tok/s | ~236 ms ~239 ms ~246 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 49 tok/s 35 tok/s 21 tok/s | ~651 ms ~659 ms ~679 ms | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 49 tok/s 35 tok/s 21 tok/s | ~651 ms ~659 ms ~679 ms | |
#245 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 49 tok/s 35 tok/s 21 tok/s | ~651 ms ~659 ms ~679 ms | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 303 tok/s 267 tok/s 212 tok/s | ~41 ms ~41 ms ~42 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 269 tok/s 225 tok/s 164 tok/s | ~64 ms ~65 ms ~66 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 269 tok/s 225 tok/s 164 tok/s | ~64 ms ~65 ms ~66 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 263 tok/s 238 tok/s 193 tok/s | ~42 ms ~42 ms ~43 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 263 tok/s 238 tok/s 193 tok/s | ~42 ms ~42 ms ~43 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 254 tok/s 208 tok/s 148 tok/s | ~76 ms ~77 ms ~79 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 253 tok/s 206 tok/s 146 tok/s | ~77 ms ~78 ms ~80 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 253 tok/s 206 tok/s 146 tok/s | ~77 ms ~78 ms ~80 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 250 tok/s 203 tok/s 143 tok/s | ~80 ms ~80 ms ~83 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 222 tok/s 173 tok/s 117 tok/s | ~107 ms ~109 ms ~112 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 222 tok/s 173 tok/s 117 tok/s | ~107 ms ~109 ms ~112 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 222 tok/s 173 tok/s 117 tok/s | ~107 ms ~109 ms ~112 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 219 tok/s 165 tok/s 107 tok/s | ~125 ms ~127 ms ~130 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 207 tok/s 159 tok/s 105 tok/s | ~125 ms ~127 ms ~130 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 207 tok/s 159 tok/s 105 tok/s | ~125 ms ~127 ms ~130 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 190 tok/s 142 tok/s 90 tok/s | ~150 ms ~152 ms ~156 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 184 tok/s 136 tok/s 86 tok/s | ~158 ms ~160 ms ~164 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 171 tok/s 124 tok/s 77 tok/s | ~181 ms ~183 ms ~188 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 171 tok/s 124 tok/s 77 tok/s | ~181 ms ~183 ms ~188 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 171 tok/s 124 tok/s 77 tok/s | ~181 ms ~183 ms ~188 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 171 tok/s 124 tok/s 77 tok/s | ~181 ms ~183 ms ~188 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 160 tok/s 114 tok/s 70 tok/s | ~203 ms ~206 ms ~211 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 160 tok/s 114 tok/s 70 tok/s | ~203 ms ~206 ms ~211 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 160 tok/s 114 tok/s 70 tok/s | ~203 ms ~206 ms ~211 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 155 tok/s 110 tok/s 67 tok/s | ~214 ms ~216 ms ~222 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 146 tok/s 102 tok/s 61 tok/s | ~237 ms ~240 ms ~246 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 146 tok/s 102 tok/s 61 tok/s | ~237 ms ~240 ms ~246 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 146 tok/s 102 tok/s 61 tok/s | ~237 ms ~240 ms ~246 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 146 tok/s 102 tok/s 61 tok/s | ~237 ms ~240 ms ~246 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 146 tok/s 102 tok/s 61 tok/s | ~237 ms ~240 ms ~246 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 146 tok/s 102 tok/s 61 tok/s | ~237 ms ~240 ms ~246 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 FP16 | 146 tok/s 102 tok/s 55 tok/s | ~265 ms ~268 ms ~321 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 146 tok/s 102 tok/s 61 tok/s | ~237 ms ~240 ms ~246 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 142 tok/s 99 tok/s 59 tok/s | ~247 ms ~250 ms ~257 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 139 tok/s 96 tok/s 57 tok/s | ~257 ms ~260 ms ~267 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 135 tok/s 92 tok/s 54 tok/s | ~268 ms ~271 ms ~279 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 129 tok/s 87 tok/s 51 tok/s | ~287 ms ~291 ms ~299 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 127 tok/s 86 tok/s 50 tok/s | ~293 ms ~297 ms ~305 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 127 tok/s 86 tok/s 50 tok/s | ~293 ms ~297 ms ~305 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 122 tok/s 79 tok/s 45 tok/s | ~337 ms ~342 ms ~352 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 120 tok/s 100 tok/s 70 tok/s | ~161 ms ~163 ms ~167 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 120 tok/s 100 tok/s 70 tok/s | ~161 ms ~163 ms ~167 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 120 tok/s 100 tok/s 70 tok/s | ~161 ms ~163 ms ~167 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 117 tok/s 77 tok/s 44 tok/s | ~338 ms ~342 ms ~352 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 | 117 tok/s 82 tok/s | ~330 ms ~334 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 115 tok/s 76 tok/s 44 tok/s | ~338 ms ~342 ms ~352 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 115 tok/s 76 tok/s 44 tok/s | ~338 ms ~342 ms ~352 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 115 tok/s 76 tok/s 44 tok/s | ~338 ms ~342 ms ~352 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 115 tok/s 76 tok/s 44 tok/s | ~338 ms ~342 ms ~352 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 115 tok/s 76 tok/s 44 tok/s | ~338 ms ~342 ms ~352 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 115 tok/s 76 tok/s 44 tok/s | ~338 ms ~342 ms ~352 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 107 tok/s | ~373 ms | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 | 100 tok/s | ~412 ms | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 | 100 tok/s | ~412 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 95 tok/s 61 tok/s 34 tok/s | ~440 ms ~446 ms ~459 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 95 tok/s 61 tok/s 34 tok/s | ~440 ms ~446 ms ~459 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 95 tok/s 61 tok/s 34 tok/s | ~440 ms ~446 ms ~459 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 95 tok/s 61 tok/s 34 tok/s | ~440 ms ~446 ms ~459 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 91 tok/s 73 tok/s 50 tok/s | ~241 ms ~243 ms ~250 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 91 tok/s | ~469 ms | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 91 tok/s | ~469 ms | |
- | Hy-Memory 30B A3B | 30B (3B active) | INT4 | 90 tok/s | ~477 ms | |
- | Hy-MT2 30B A3B | 30B (3B active) | INT4 | 90 tok/s | ~477 ms | |
- | MiniCPM-V 4.7 35B A3B | 35B (3B active) | INT4 | 84 tok/s | ~525 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 28 tok/s | ~542 ms ~550 ms ~566 ms | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 28 tok/s | ~542 ms ~550 ms ~566 ms | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 28 tok/s | ~542 ms ~550 ms ~566 ms | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 79 tok/s 62 tok/s 40 tok/s | ~312 ms ~316 ms ~324 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 75 tok/s 58 tok/s 37 tok/s | ~343 ms ~347 ms ~356 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 75 tok/s 58 tok/s 37 tok/s | ~343 ms ~347 ms ~356 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 65 tok/s 39 tok/s 21 tok/s | ~746 ms ~756 ms ~779 ms | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 64 tok/s 39 tok/s 21 tok/s | ~726 ms ~736 ms ~758 ms | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 64 tok/s 39 tok/s 21 tok/s | ~726 ms ~736 ms ~758 ms | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 62 tok/s 38 tok/s 20 tok/s | ~747 ms ~757 ms ~780 ms | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 62 tok/s 38 tok/s 20 tok/s | ~747 ms ~757 ms ~780 ms | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 60 tok/s 36 tok/s 19 tok/s | ~777 ms ~787 ms ~811 ms | |
- | Youtu Parsing Omni | 8B | INT4 Q8 FP16 | 57 tok/s 34 tok/s 17 tok/s | ~848 ms ~860 ms ~960 ms | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 FP16 | 55 tok/s 33 tok/s 17 tok/s | ~859 ms ~871 ms ~972 ms | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 FP16 | 55 tok/s 33 tok/s 17 tok/s | ~859 ms ~871 ms ~972 ms | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 FP16 | 50 tok/s 30 tok/s 14 tok/s | ~952 ms ~966 ms ~1.2s | |
- | LensVLM 9B | 9B | INT4 Q8 FP16 | 50 tok/s 30 tok/s 14 tok/s | ~952 ms ~966 ms ~1.2s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 FP16 | 50 tok/s 30 tok/s 14 tok/s | ~952 ms ~966 ms ~1.2s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 49 tok/s 35 tok/s 21 tok/s | ~651 ms ~659 ms ~679 ms | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 49 tok/s 35 tok/s 21 tok/s | ~651 ms ~659 ms ~679 ms | |
- | Falcon3-10B | 10B | INT4 Q8 | 46 tok/s 27 tok/s | ~1.1s ~1.1s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 Q8 | 46 tok/s 36 tok/s | ~407 ms ~480 ms | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 46 tok/s 27 tok/s | ~1.1s ~1.1s | |
- | Falcon2-11B | 11B | INT4 Q8 | 44 tok/s 26 tok/s | ~1.2s ~1.2s | |
- | Hunyuan Lite | 7B | INT4 Q8 FP16 | 44 tok/s 31 tok/s 17 tok/s | ~753 ms ~763 ms ~852 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 FP16 | 44 tok/s 31 tok/s 17 tok/s | ~753 ms ~763 ms ~852 ms | |
- | SEA-LION-7B | 7.1B | INT4 Q8 FP16 | 44 tok/s 30 tok/s 17 tok/s | ~763 ms ~773 ms ~863 ms | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 FP16 | 44 tok/s 30 tok/s 17 tok/s | ~763 ms ~773 ms ~863 ms | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 | 40 tok/s 23 tok/s | ~1.3s ~1.3s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 | 40 tok/s 23 tok/s | ~1.3s ~1.3s | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 | 40 tok/s 23 tok/s | ~1.3s ~1.3s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 | 40 tok/s 23 tok/s | ~1.3s ~1.3s | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 | 40 tok/s 23 tok/s | ~1.3s ~1.3s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 FP16 | 40 tok/s 27 tok/s 14 tok/s | ~856 ms ~867 ms ~1.0s | |
- | Typhoon-2-8B | 8B | INT4 Q8 FP16 | 40 tok/s 27 tok/s 14 tok/s | ~856 ms ~867 ms ~1.0s | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 37 tok/s 21 tok/s | ~1.4s ~1.4s | |
- | GLM-4-9B | 9B | INT4 Q8 | 36 tok/s 25 tok/s | ~960 ms ~973 ms | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 | 36 tok/s 25 tok/s | ~960 ms ~973 ms | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 | 36 tok/s 25 tok/s | ~960 ms ~973 ms | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 | 36 tok/s 24 tok/s | ~980 ms ~993 ms | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 | 36 tok/s 24 tok/s | ~980 ms ~993 ms | |
- | Yi-9B | 9B | INT4 Q8 | 36 tok/s 25 tok/s | ~960 ms ~973 ms | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 34 tok/s 20 tok/s | ~1.5s ~1.5s | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 34 tok/s 20 tok/s | ~1.5s ~1.5s | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 34 tok/s 20 tok/s | ~1.5s ~1.5s | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 32 tok/s 18 tok/s | ~1.6s ~1.7s | |
- | GreenMind-14B-R1 | 14B | INT4 Q8 | 25 tok/s 16 tok/s | ~1.5s ~1.6s | |
- | Arete 27B | 27B | INT4 | 19 tok/s | ~2.8s | |
- | AREX-2 | 27B | INT4 | 19 tok/s | ~2.8s | |
- | PPLX Decider v1 27B | 27B | INT4 | 19 tok/s | ~2.8s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 19 tok/s | ~2.8s | |
- | Agnes 3.0 Flash | 33B | INT4 | 15 tok/s | ~3.7s | |
Inference Capacity
Maximum model parameter class runnable by weight precision.
Context:
4-bit
14B 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
8B Models
Full Parameter Training
1B Models
Workload Recommendations
Guidance for optimal precision and operational ceilings on NVIDIA RTX 4000 Ada Generation (20GB).
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 360 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 80 tok/s on an 8B Q4 model and 9 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning