NVIDIA RTX 2000 Ada Generation (16GB)
The NVIDIA RTX 2000 Ada Generation (16GB) features 16 GB of dedicated VRAM and 224 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
224 GB/s
Max Inference Class
14B Models (Q4)
TDP
70W
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 2000 Ada Generation (16GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA RTX 2000 Ada Generation (16GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#48 | Qwen 3.8 27B | 27B | INT4 | 11 tok/s | ~7.2s | |
#93 | Qwen3.5-27B | 27B | INT4 | 11 tok/s | ~7.2s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 | 1 tok/s | ~73.0s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 | 16 tok/s | ~3.3s | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 55 tok/s | ~1.2s | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 | 33 tok/s 19 tok/s | ~2.1s ~2.1s | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 41 tok/s 24 tok/s 12 tok/s | ~1.6s ~1.7s ~2.0s | |
#135 | Gemma 4 12B | 11.95B | INT4 Q8 | 18 tok/s 11 tok/s | ~2.8s ~3.3s | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 65 tok/s 40 tok/s 22 tok/s | ~963 ms ~973 ms ~994 ms | |
#143 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 23 tok/s | ~1.2s | |
#144 | GLM-4V | 9B | INT4 Q8 | 23 tok/s 15 tok/s | ~2.1s ~2.3s | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 10 tok/s 6 tok/s 3 tok/s | ~6.6s ~6.7s ~6.8s | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 | 37 tok/s 22 tok/s | ~1.9s ~1.9s | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 | 37 tok/s 22 tok/s | ~1.9s ~1.9s | |
#166 | Phi-4 | 14B | INT4 Q8 | 22 tok/s 11 tok/s | ~3.2s ~3.8s | |
#167 | Gemma 3 27B | 27B | INT4 | 11 tok/s | ~7.2s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 | 29 tok/s 20 tok/s | ~1.7s ~1.7s | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 23 tok/s 12 tok/s | ~3.2s ~3.8s | |
#183 | Ministral 3 14B | 14B | INT4 | 16 tok/s | ~3.3s | |
#186 | Gemma 3 12B | 12B | INT4 Q8 | 26 tok/s 14 tok/s | ~2.8s ~3.0s | |
#188 | Mistral-Small-2501 | 24B | INT4 | 13 tok/s | ~5.9s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 | 26 tok/s 18 tok/s | ~1.9s ~1.9s | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~514 ms ~518 ms ~529 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~514 ms ~518 ms ~529 ms | |
#193 | Gemma 2 27B | 27B | INT4 | 11 tok/s | ~7.2s | |
#194 | Qwen2.5-14B | 14B | INT4 Q8 | 22 tok/s 11 tok/s | ~3.2s ~3.8s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 54 tok/s 33 tok/s 17 tok/s | ~1.2s ~1.2s ~1.3s | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 | 38 tok/s 22 tok/s | ~1.9s ~1.9s | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 65 tok/s 40 tok/s 22 tok/s | ~963 ms ~973 ms ~994 ms | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 51 tok/s 38 tok/s 24 tok/s | ~745 ms ~751 ms ~767 ms | |
#207 | Gemma 2 9B | 9B | INT4 Q8 | 33 tok/s 19 tok/s | ~2.1s ~2.1s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 186 tok/s 137 tok/s 87 tok/s | ~212 ms ~214 ms ~218 ms | |
#209 | Qwen3-14B | 14B | INT4 Q8 | 22 tok/s 11 tok/s | ~3.2s ~3.8s | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 65 tok/s 40 tok/s 22 tok/s | ~963 ms ~973 ms ~994 ms | |
#211 | Qwen3-8B | 8B | INT4 Q8 | 37 tok/s 22 tok/s | ~1.9s ~1.9s | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 42 tok/s 25 tok/s 12 tok/s | ~1.6s ~1.7s ~1.8s | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 119 tok/s 81 tok/s 47 tok/s | ~440 ms ~444 ms ~453 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 | 37 tok/s 22 tok/s | ~1.9s ~1.9s | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 235 tok/s 207 tok/s 160 tok/s | ~74 ms ~75 ms ~76 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 214 tok/s 164 tok/s 108 tok/s | ~158 ms ~159 ms ~163 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 | 37 tok/s 22 tok/s | ~1.9s ~1.9s | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 68 tok/s 42 tok/s 23 tok/s | ~918 ms ~927 ms ~947 ms | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 41 tok/s 24 tok/s 12 tok/s | ~1.6s ~1.7s ~2.0s | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 | 37 tok/s 22 tok/s | ~1.9s ~1.9s | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 129 tok/s 89 tok/s 52 tok/s | ~390 ms ~393 ms ~401 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 28 tok/s | ~738 ms ~745 ms ~760 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 68 tok/s 42 tok/s 23 tok/s | ~918 ms ~927 ms ~947 ms | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 51 tok/s 42 tok/s 28 tok/s | ~558 ms ~562 ms ~620 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 40 tok/s 24 tok/s 11 tok/s | ~1.7s ~1.7s ~2.1s | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 163 tok/s 118 tok/s 73 tok/s | ~268 ms ~270 ms ~275 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~514 ms ~518 ms ~529 ms | |
#233 | Phi-3-medium | 14B | INT4 Q8 | 22 tok/s 11 tok/s | ~3.2s ~3.8s | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 | 29 tok/s 20 tok/s | ~1.7s ~1.7s | |
#236 | Qwen2-7B | 7B | INT4 Q8 FP16 | 41 tok/s 24 tok/s 12 tok/s | ~1.6s ~1.7s ~2.0s | |
#237 | Phi-3-small | 7B | INT4 Q8 FP16 | 41 tok/s 24 tok/s 12 tok/s | ~1.6s ~1.7s ~2.0s | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 163 tok/s 118 tok/s 73 tok/s | ~268 ms ~270 ms ~275 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 40 tok/s 24 tok/s 11 tok/s | ~1.7s ~1.7s ~2.1s | |
#241 | Gemma 1 7B | 7B | INT4 Q8 | 29 tok/s 20 tok/s | ~1.7s ~1.7s | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 116 tok/s 75 tok/s 42 tok/s | ~513 ms ~518 ms ~528 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 32 tok/s 22 tok/s 12 tok/s | ~1.4s ~1.4s ~1.6s | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 32 tok/s 22 tok/s 12 tok/s | ~1.4s ~1.4s ~1.6s | |
#245 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 32 tok/s 22 tok/s 12 tok/s | ~1.4s ~1.4s ~1.6s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 272 tok/s 228 tok/s 168 tok/s | ~81 ms ~82 ms ~84 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 231 tok/s 181 tok/s 123 tok/s | ~132 ms ~133 ms ~136 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 231 tok/s 181 tok/s 123 tok/s | ~132 ms ~133 ms ~136 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 224 tok/s 196 tok/s 150 tok/s | ~82 ms ~83 ms ~84 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 224 tok/s 196 tok/s 150 tok/s | ~82 ms ~83 ms ~84 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 214 tok/s 164 tok/s 108 tok/s | ~158 ms ~159 ms ~163 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 212 tok/s 163 tok/s 107 tok/s | ~160 ms ~162 ms ~165 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 212 tok/s 163 tok/s 107 tok/s | ~160 ms ~162 ms ~165 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 209 tok/s 159 tok/s 104 tok/s | ~167 ms ~168 ms ~171 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 178 tok/s 131 tok/s 82 tok/s | ~228 ms ~230 ms ~235 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 178 tok/s 131 tok/s 82 tok/s | ~228 ms ~230 ms ~235 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 178 tok/s 131 tok/s 82 tok/s | ~228 ms ~230 ms ~235 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 176 tok/s 124 tok/s 75 tok/s | ~267 ms ~270 ms ~275 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 163 tok/s 118 tok/s 73 tok/s | ~268 ms ~270 ms ~275 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 163 tok/s 118 tok/s 73 tok/s | ~268 ms ~270 ms ~275 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 146 tok/s 103 tok/s 62 tok/s | ~322 ms ~325 ms ~331 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 141 tok/s 99 tok/s 59 tok/s | ~340 ms ~343 ms ~350 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 129 tok/s 89 tok/s 52 tok/s | ~390 ms ~393 ms ~401 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 129 tok/s 89 tok/s 52 tok/s | ~390 ms ~393 ms ~401 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 129 tok/s 89 tok/s 52 tok/s | ~390 ms ~393 ms ~401 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 129 tok/s 89 tok/s 52 tok/s | ~390 ms ~393 ms ~401 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 119 tok/s 81 tok/s 47 tok/s | ~440 ms ~444 ms ~453 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 119 tok/s 81 tok/s 47 tok/s | ~440 ms ~444 ms ~453 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 119 tok/s 81 tok/s 47 tok/s | ~440 ms ~444 ms ~453 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 115 tok/s 77 tok/s 45 tok/s | ~463 ms ~467 ms ~477 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~514 ms ~518 ms ~529 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~514 ms ~518 ms ~529 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~514 ms ~518 ms ~529 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~514 ms ~518 ms ~529 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~514 ms ~518 ms ~529 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~514 ms ~518 ms ~529 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 | 107 tok/s 71 tok/s | ~578 ms ~582 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 107 tok/s 71 tok/s 41 tok/s | ~514 ms ~518 ms ~529 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 104 tok/s 68 tok/s 39 tok/s | ~536 ms ~541 ms ~552 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 100 tok/s 66 tok/s 37 tok/s | ~558 ms ~564 ms ~575 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 97 tok/s 64 tok/s 36 tok/s | ~583 ms ~588 ms ~601 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 92 tok/s 60 tok/s 33 tok/s | ~626 ms ~632 ms ~645 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 91 tok/s 59 tok/s 33 tok/s | ~639 ms ~645 ms ~658 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 91 tok/s 59 tok/s 33 tok/s | ~639 ms ~645 ms ~658 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 87 tok/s 54 tok/s 29 tok/s | ~737 ms ~744 ms ~760 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 85 tok/s 69 tok/s 47 tok/s | ~345 ms ~348 ms ~354 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 85 tok/s 69 tok/s 47 tok/s | ~345 ms ~348 ms ~354 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 85 tok/s 69 tok/s 47 tok/s | ~345 ms ~348 ms ~354 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 | 83 tok/s 53 tok/s | ~720 ms ~788 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 82 tok/s 52 tok/s 29 tok/s | ~737 ms ~744 ms ~760 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 28 tok/s | ~738 ms ~745 ms ~760 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 28 tok/s | ~738 ms ~745 ms ~760 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 28 tok/s | ~738 ms ~745 ms ~760 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 28 tok/s | ~738 ms ~745 ms ~760 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 28 tok/s | ~738 ms ~745 ms ~760 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 81 tok/s 51 tok/s 28 tok/s | ~738 ms ~745 ms ~760 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 71 tok/s | ~886 ms | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 | 66 tok/s | ~978 ms | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 | 66 tok/s | ~978 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 65 tok/s 40 tok/s 22 tok/s | ~963 ms ~973 ms ~994 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 65 tok/s 40 tok/s 22 tok/s | ~963 ms ~973 ms ~994 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 65 tok/s 40 tok/s 22 tok/s | ~963 ms ~973 ms ~994 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 65 tok/s 40 tok/s 22 tok/s | ~963 ms ~973 ms ~994 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 62 tok/s 49 tok/s 33 tok/s | ~520 ms ~525 ms ~535 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 60 tok/s | ~1.1s | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 60 tok/s | ~1.1s | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 55 tok/s 33 tok/s 18 tok/s | ~1.2s ~1.2s ~1.2s | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 55 tok/s 33 tok/s 18 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 55 tok/s 33 tok/s 18 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 54 tok/s 41 tok/s 26 tok/s | ~678 ms ~683 ms ~698 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 51 tok/s 38 tok/s 24 tok/s | ~745 ms ~751 ms ~767 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 51 tok/s 38 tok/s 24 tok/s | ~745 ms ~751 ms ~767 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 43 tok/s 25 tok/s 12 tok/s | ~1.6s ~1.7s ~1.8s | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 42 tok/s 25 tok/s 13 tok/s | ~1.6s ~1.6s ~1.8s | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 42 tok/s 25 tok/s 13 tok/s | ~1.6s ~1.6s ~1.8s | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 41 tok/s 24 tok/s 12 tok/s | ~1.6s ~1.7s ~2.0s | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 41 tok/s 24 tok/s 12 tok/s | ~1.6s ~1.7s ~2.0s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 40 tok/s 24 tok/s 11 tok/s | ~1.7s ~1.7s ~2.1s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 | 38 tok/s 22 tok/s | ~1.9s ~1.9s | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 | 36 tok/s 21 tok/s | ~1.9s ~1.9s | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 | 36 tok/s 21 tok/s | ~1.9s ~1.9s | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 | 33 tok/s 19 tok/s | ~2.1s ~2.1s | |
- | LensVLM 9B | 9B | INT4 Q8 | 33 tok/s 19 tok/s | ~2.1s ~2.1s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 | 33 tok/s 19 tok/s | ~2.1s ~2.1s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 32 tok/s 22 tok/s 12 tok/s | ~1.4s ~1.4s ~1.6s | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 32 tok/s 22 tok/s 12 tok/s | ~1.4s ~1.4s ~1.6s | |
- | Falcon3-10B | 10B | INT4 Q8 | 30 tok/s 18 tok/s | ~2.3s ~2.3s | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 30 tok/s 18 tok/s | ~2.3s ~2.3s | |
- | Falcon2-11B | 11B | INT4 Q8 | 29 tok/s 16 tok/s | ~2.5s ~2.6s | |
- | Hunyuan Lite | 7B | INT4 Q8 | 29 tok/s 20 tok/s | ~1.7s ~1.7s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 | 29 tok/s | ~959 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 | 29 tok/s 20 tok/s | ~1.7s ~1.7s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 | 28 tok/s 19 tok/s | ~1.7s ~1.7s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 | 28 tok/s 19 tok/s | ~1.7s ~1.7s | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 | 26 tok/s 14 tok/s | ~2.8s ~3.0s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 | 26 tok/s 14 tok/s | ~2.8s ~3.0s | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 | 26 tok/s 14 tok/s | ~2.8s ~3.0s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 | 26 tok/s 14 tok/s | ~2.8s ~3.0s | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 | 26 tok/s 14 tok/s | ~2.8s ~3.0s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 | 26 tok/s 18 tok/s | ~1.9s ~1.9s | |
- | Typhoon-2-8B | 8B | INT4 Q8 | 26 tok/s 18 tok/s | ~1.9s ~1.9s | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 24 tok/s 13 tok/s | ~3.0s ~3.3s | |
- | GLM-4-9B | 9B | INT4 Q8 | 23 tok/s 15 tok/s | ~2.1s ~2.3s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 | 23 tok/s 15 tok/s | ~2.1s ~2.3s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 | 23 tok/s 15 tok/s | ~2.1s ~2.3s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 | 23 tok/s 15 tok/s | ~2.2s ~2.4s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 | 23 tok/s 15 tok/s | ~2.2s ~2.4s | |
- | Yi-9B | 9B | INT4 Q8 | 23 tok/s 15 tok/s | ~2.1s ~2.3s | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 22 tok/s 11 tok/s | ~3.2s ~3.8s | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 22 tok/s 11 tok/s | ~3.2s ~3.8s | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 22 tok/s 11 tok/s | ~3.2s ~3.8s | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 21 tok/s 11 tok/s | ~3.5s ~4.1s | |
- | GreenMind-14B-R1 | 14B | INT4 | 16 tok/s | ~3.3s | |
- | Arete 27B | 27B | INT4 | 11 tok/s | ~7.2s | |
- | AREX-2 | 27B | INT4 | 11 tok/s | ~7.2s | |
- | PPLX Decider v1 27B | 27B | INT4 | 11 tok/s | ~7.2s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 11 tok/s | ~7.2s | |
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 2000 Ada Generation (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 224 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 50 tok/s on an 8B Q4 model and 6 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning