NVIDIA T4 (16GB)
The NVIDIA T4 (16GB) features 16 GB of dedicated VRAM and 320 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
320 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 T4 (16GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA T4 (16GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#48 | Qwen 3.8 27B | 27B | INT4 | 15 tok/s | ~6.1s | |
#93 | Qwen3.5-27B | 27B | INT4 | 15 tok/s | ~6.1s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 | 1 tok/s | ~61.4s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 | 22 tok/s | ~2.7s | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 78 tok/s | ~1.0s | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 | 46 tok/s 26 tok/s | ~1.8s ~1.8s | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 57 tok/s 33 tok/s 16 tok/s | ~1.4s ~1.4s ~1.7s | |
#135 | Gemma 4 12B | 11.95B | INT4 Q8 | 25 tok/s 15 tok/s | ~2.3s ~2.8s | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 92 tok/s 56 tok/s 30 tok/s | ~807 ms ~814 ms ~830 ms | |
#143 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 32 tok/s | ~1.0s | |
#144 | GLM-4V | 9B | INT4 Q8 | 32 tok/s 20 tok/s | ~1.8s ~1.9s | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 14 tok/s 8 tok/s 4 tok/s | ~5.5s ~5.6s ~5.7s | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 | 51 tok/s 30 tok/s | ~1.6s ~1.6s | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 | 51 tok/s 30 tok/s | ~1.6s ~1.6s | |
#166 | Phi-4 | 14B | INT4 Q8 | 30 tok/s 16 tok/s | ~2.7s ~3.2s | |
#167 | Gemma 3 27B | 27B | INT4 | 15 tok/s | ~6.1s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 | 39 tok/s 27 tok/s | ~1.4s ~1.4s | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 31 tok/s 16 tok/s | ~2.7s ~3.2s | |
#183 | Ministral 3 14B | 14B | INT4 | 22 tok/s | ~2.7s | |
#186 | Gemma 3 12B | 12B | INT4 Q8 | 35 tok/s 19 tok/s | ~2.3s ~2.6s | |
#188 | Mistral-Small-2501 | 24B | INT4 | 17 tok/s | ~5.0s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 | 35 tok/s 24 tok/s | ~1.6s ~1.6s | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 155 tok/s 100 tok/s 56 tok/s | ~429 ms ~433 ms ~441 ms | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 155 tok/s 100 tok/s 56 tok/s | ~429 ms ~433 ms ~441 ms | |
#193 | Gemma 2 27B | 27B | INT4 | 15 tok/s | ~6.1s | |
#194 | Qwen2.5-14B | 14B | INT4 Q8 | 30 tok/s 16 tok/s | ~2.7s ~3.2s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 75 tok/s 45 tok/s 24 tok/s | ~1.0s ~1.0s ~1.0s | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 | 52 tok/s 30 tok/s | ~1.6s ~1.6s | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 92 tok/s 56 tok/s 30 tok/s | ~807 ms ~814 ms ~830 ms | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 71 tok/s 53 tok/s 33 tok/s | ~623 ms ~628 ms ~640 ms | |
#207 | Gemma 2 9B | 9B | INT4 Q8 | 46 tok/s 26 tok/s | ~1.8s ~1.8s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 286 tok/s 204 tok/s 125 tok/s | ~175 ms ~177 ms ~180 ms | |
#209 | Qwen3-14B | 14B | INT4 Q8 | 30 tok/s 16 tok/s | ~2.7s ~3.2s | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 92 tok/s 56 tok/s 30 tok/s | ~807 ms ~814 ms ~830 ms | |
#211 | Qwen3-8B | 8B | INT4 Q8 | 51 tok/s 30 tok/s | ~1.6s ~1.6s | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 59 tok/s 34 tok/s 17 tok/s | ~1.4s ~1.4s ~1.5s | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 174 tok/s 115 tok/s 65 tok/s | ~367 ms ~370 ms ~377 ms | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 | 51 tok/s 30 tok/s | ~1.6s ~1.6s | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 377 tok/s 324 tok/s 241 tok/s | ~59 ms ~60 ms ~61 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 336 tok/s 248 tok/s 157 tok/s | ~130 ms ~131 ms ~133 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 | 51 tok/s 30 tok/s | ~1.6s ~1.6s | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 96 tok/s 58 tok/s 31 tok/s | ~769 ms ~776 ms ~791 ms | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 57 tok/s 33 tok/s 16 tok/s | ~1.4s ~1.4s ~1.7s | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 | 51 tok/s 30 tok/s | ~1.6s ~1.6s | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 191 tok/s 127 tok/s 73 tok/s | ~325 ms ~328 ms ~333 ms | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 116 tok/s 72 tok/s 39 tok/s | ~618 ms ~623 ms ~635 ms | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 96 tok/s 58 tok/s 31 tok/s | ~769 ms ~776 ms ~791 ms | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 71 tok/s 59 tok/s 38 tok/s | ~466 ms ~468 ms ~517 ms | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 55 tok/s 32 tok/s 15 tok/s | ~1.4s ~1.4s ~1.7s | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 247 tok/s 172 tok/s 103 tok/s | ~222 ms ~224 ms ~228 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 155 tok/s 100 tok/s 56 tok/s | ~429 ms ~433 ms ~441 ms | |
#233 | Phi-3-medium | 14B | INT4 Q8 | 30 tok/s 16 tok/s | ~2.7s ~3.2s | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 | 39 tok/s 27 tok/s | ~1.4s ~1.4s | |
#236 | Qwen2-7B | 7B | INT4 Q8 FP16 | 57 tok/s 33 tok/s 16 tok/s | ~1.4s ~1.4s ~1.7s | |
#237 | Phi-3-small | 7B | INT4 Q8 FP16 | 57 tok/s 33 tok/s 16 tok/s | ~1.4s ~1.4s ~1.7s | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 247 tok/s 172 tok/s 103 tok/s | ~222 ms ~224 ms ~228 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 55 tok/s 32 tok/s 15 tok/s | ~1.4s ~1.4s ~1.7s | |
#241 | Gemma 1 7B | 7B | INT4 Q8 | 39 tok/s 27 tok/s | ~1.4s ~1.4s | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 169 tok/s 106 tok/s 58 tok/s | ~429 ms ~432 ms ~440 ms | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 44 tok/s 31 tok/s 17 tok/s | ~1.2s ~1.2s ~1.3s | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 44 tok/s 31 tok/s 17 tok/s | ~1.2s ~1.2s ~1.3s | |
#245 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 44 tok/s 31 tok/s 17 tok/s | ~1.2s ~1.2s ~1.3s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 450 tok/s 364 tok/s 255 tok/s | ~65 ms ~66 ms ~67 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 368 tok/s 278 tok/s 180 tok/s | ~108 ms ~109 ms ~111 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 368 tok/s 278 tok/s 180 tok/s | ~108 ms ~109 ms ~111 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 355 tok/s 304 tok/s 224 tok/s | ~66 ms ~67 ms ~68 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 355 tok/s 304 tok/s 224 tok/s | ~66 ms ~67 ms ~68 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 336 tok/s 248 tok/s 157 tok/s | ~130 ms ~131 ms ~133 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 334 tok/s 246 tok/s 155 tok/s | ~132 ms ~133 ms ~135 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 334 tok/s 246 tok/s 155 tok/s | ~132 ms ~133 ms ~135 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 327 tok/s 240 tok/s 151 tok/s | ~137 ms ~138 ms ~141 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 273 tok/s 194 tok/s 117 tok/s | ~189 ms ~191 ms ~194 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 273 tok/s 194 tok/s 117 tok/s | ~189 ms ~191 ms ~194 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 273 tok/s 194 tok/s 117 tok/s | ~189 ms ~191 ms ~194 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 268 tok/s 182 tok/s 106 tok/s | ~222 ms ~224 ms ~228 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 247 tok/s 172 tok/s 103 tok/s | ~222 ms ~224 ms ~228 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 247 tok/s 172 tok/s 103 tok/s | ~222 ms ~224 ms ~228 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 218 tok/s 149 tok/s 87 tok/s | ~268 ms ~270 ms ~275 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 210 tok/s 142 tok/s 83 tok/s | ~283 ms ~285 ms ~291 ms | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 191 tok/s 127 tok/s 73 tok/s | ~325 ms ~328 ms ~333 ms | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 191 tok/s 127 tok/s 73 tok/s | ~325 ms ~328 ms ~333 ms | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 191 tok/s 127 tok/s 73 tok/s | ~325 ms ~328 ms ~333 ms | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 191 tok/s 127 tok/s 73 tok/s | ~325 ms ~328 ms ~333 ms | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 174 tok/s 115 tok/s 65 tok/s | ~367 ms ~370 ms ~377 ms | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 174 tok/s 115 tok/s 65 tok/s | ~367 ms ~370 ms ~377 ms | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 174 tok/s 115 tok/s 65 tok/s | ~367 ms ~370 ms ~377 ms | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 168 tok/s 110 tok/s 62 tok/s | ~387 ms ~390 ms ~397 ms | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 155 tok/s 100 tok/s 56 tok/s | ~429 ms ~433 ms ~441 ms | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 155 tok/s 100 tok/s 56 tok/s | ~429 ms ~433 ms ~441 ms | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 155 tok/s 100 tok/s 56 tok/s | ~429 ms ~433 ms ~441 ms | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 155 tok/s 100 tok/s 56 tok/s | ~429 ms ~433 ms ~441 ms | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 155 tok/s 100 tok/s 56 tok/s | ~429 ms ~433 ms ~441 ms | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 155 tok/s 100 tok/s 56 tok/s | ~429 ms ~433 ms ~441 ms | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 | 155 tok/s 100 tok/s | ~483 ms ~487 ms | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 155 tok/s 100 tok/s 56 tok/s | ~429 ms ~433 ms ~441 ms | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 150 tok/s 96 tok/s 54 tok/s | ~448 ms ~452 ms ~460 ms | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 145 tok/s 93 tok/s 52 tok/s | ~467 ms ~471 ms ~479 ms | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 140 tok/s 89 tok/s 49 tok/s | ~488 ms ~492 ms ~501 ms | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 132 tok/s 84 tok/s 46 tok/s | ~523 ms ~528 ms ~537 ms | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 130 tok/s 82 tok/s 45 tok/s | ~535 ms ~539 ms ~549 ms | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 130 tok/s 82 tok/s 45 tok/s | ~535 ms ~539 ms ~549 ms | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 124 tok/s 75 tok/s 40 tok/s | ~617 ms ~622 ms ~634 ms | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 121 tok/s 98 tok/s 65 tok/s | ~287 ms ~289 ms ~294 ms | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 121 tok/s 98 tok/s 65 tok/s | ~287 ms ~289 ms ~294 ms | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 121 tok/s 98 tok/s 65 tok/s | ~287 ms ~289 ms ~294 ms | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 118 tok/s 72 tok/s 39 tok/s | ~617 ms ~623 ms ~634 ms | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 | 118 tok/s 74 tok/s | ~603 ms ~660 ms | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 116 tok/s 72 tok/s 39 tok/s | ~618 ms ~623 ms ~635 ms | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 116 tok/s 72 tok/s 39 tok/s | ~618 ms ~623 ms ~635 ms | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 116 tok/s 72 tok/s 39 tok/s | ~618 ms ~623 ms ~635 ms | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 116 tok/s 72 tok/s 39 tok/s | ~618 ms ~623 ms ~635 ms | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 116 tok/s 72 tok/s 39 tok/s | ~618 ms ~623 ms ~635 ms | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 116 tok/s 72 tok/s 39 tok/s | ~618 ms ~623 ms ~635 ms | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 101 tok/s | ~743 ms | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 | 93 tok/s | ~820 ms | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 | 93 tok/s | ~820 ms | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 92 tok/s 56 tok/s 30 tok/s | ~807 ms ~814 ms ~830 ms | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 92 tok/s 56 tok/s 30 tok/s | ~807 ms ~814 ms ~830 ms | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 92 tok/s 56 tok/s 30 tok/s | ~807 ms ~814 ms ~830 ms | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 92 tok/s 56 tok/s 30 tok/s | ~807 ms ~814 ms ~830 ms | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 87 tok/s 69 tok/s 45 tok/s | ~434 ms ~437 ms ~445 ms | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 84 tok/s | ~934 ms | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 84 tok/s | ~934 ms | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 76 tok/s 46 tok/s 24 tok/s | ~997 ms ~1.0s ~1.0s | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 76 tok/s 46 tok/s 24 tok/s | ~997 ms ~1.0s ~1.0s | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 76 tok/s 46 tok/s 24 tok/s | ~997 ms ~1.0s ~1.0s | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 75 tok/s 57 tok/s 35 tok/s | ~566 ms ~571 ms ~581 ms | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 71 tok/s 53 tok/s 33 tok/s | ~623 ms ~628 ms ~640 ms | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 71 tok/s 53 tok/s 33 tok/s | ~623 ms ~628 ms ~640 ms | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 60 tok/s 34 tok/s 17 tok/s | ~1.4s ~1.4s ~1.5s | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 59 tok/s 34 tok/s 17 tok/s | ~1.3s ~1.4s ~1.5s | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 59 tok/s 34 tok/s 17 tok/s | ~1.3s ~1.4s ~1.5s | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 57 tok/s 33 tok/s 16 tok/s | ~1.4s ~1.4s ~1.7s | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 57 tok/s 33 tok/s 16 tok/s | ~1.4s ~1.4s ~1.7s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 55 tok/s 32 tok/s 15 tok/s | ~1.4s ~1.4s ~1.7s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 | 52 tok/s 30 tok/s | ~1.6s ~1.6s | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 | 50 tok/s 29 tok/s | ~1.6s ~1.6s | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 | 50 tok/s 29 tok/s | ~1.6s ~1.6s | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 | 46 tok/s 26 tok/s | ~1.8s ~1.8s | |
- | LensVLM 9B | 9B | INT4 Q8 | 46 tok/s 26 tok/s | ~1.8s ~1.8s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 | 46 tok/s 26 tok/s | ~1.8s ~1.8s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 44 tok/s 31 tok/s 17 tok/s | ~1.2s ~1.2s ~1.3s | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 44 tok/s 31 tok/s 17 tok/s | ~1.2s ~1.2s ~1.3s | |
- | Falcon3-10B | 10B | INT4 Q8 | 41 tok/s 24 tok/s | ~1.9s ~2.0s | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 41 tok/s 24 tok/s | ~1.9s ~2.0s | |
- | Falcon2-11B | 11B | INT4 Q8 | 40 tok/s 22 tok/s | ~2.1s ~2.2s | |
- | Hunyuan Lite | 7B | INT4 Q8 | 39 tok/s 27 tok/s | ~1.4s ~1.4s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 | 39 tok/s | ~802 ms | |
- | OLMo 3 7B Base | 7B | INT4 Q8 | 39 tok/s 27 tok/s | ~1.4s ~1.4s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 | 39 tok/s 27 tok/s | ~1.4s ~1.4s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 | 39 tok/s 27 tok/s | ~1.4s ~1.4s | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 | 35 tok/s 19 tok/s | ~2.3s ~2.5s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 | 35 tok/s 19 tok/s | ~2.3s ~2.5s | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 | 35 tok/s 19 tok/s | ~2.3s ~2.5s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 | 35 tok/s 19 tok/s | ~2.3s ~2.5s | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 | 35 tok/s 19 tok/s | ~2.3s ~2.5s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 | 35 tok/s 24 tok/s | ~1.6s ~1.6s | |
- | Typhoon-2-8B | 8B | INT4 Q8 | 35 tok/s 24 tok/s | ~1.6s ~1.6s | |
- | GLM-4-9B | 9B | INT4 Q8 | 32 tok/s 20 tok/s | ~1.8s ~1.9s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 | 32 tok/s 20 tok/s | ~1.8s ~1.9s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 | 32 tok/s 20 tok/s | ~1.8s ~1.9s | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 32 tok/s 18 tok/s | ~2.5s ~2.8s | |
- | Yi-9B | 9B | INT4 Q8 | 32 tok/s 20 tok/s | ~1.8s ~1.9s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 | 31 tok/s 20 tok/s | ~1.8s ~2.0s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 | 31 tok/s 20 tok/s | ~1.8s ~2.0s | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 30 tok/s 16 tok/s | ~2.7s ~3.2s | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 30 tok/s 16 tok/s | ~2.7s ~3.2s | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 30 tok/s 16 tok/s | ~2.7s ~3.2s | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 28 tok/s 15 tok/s | ~2.9s ~3.4s | |
- | GreenMind-14B-R1 | 14B | INT4 | 22 tok/s | ~2.7s | |
- | Arete 27B | 27B | INT4 | 15 tok/s | ~6.1s | |
- | AREX-2 | 27B | INT4 | 15 tok/s | ~6.1s | |
- | PPLX Decider v1 27B | 27B | INT4 | 15 tok/s | ~6.1s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 15 tok/s | ~6.1s | |
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 T4 (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 320 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 71 tok/s on an 8B Q4 model and 8 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning