NVIDIA A2 (16GB)
The NVIDIA A2 (16GB) features 16 GB of dedicated VRAM and 200 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
200 GB/s
Max Inference Class
14B Models (Q4)
TDP
60W
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 A2 (16GB)
Inference throughput, memory compatibility, and generation speeds for open-weights LLMs on NVIDIA A2 (16GB).
Sort by:
Context:
KV Cache:
GPUs:
| Rank | Model | Parameters | Precision | TPS (Approx.) | TTFT | Can Run |
|---|---|---|---|---|---|---|
#48 | Qwen 3.8 27B | 27B | INT4 | 9 tok/s | ~21.8s | |
#93 | Qwen3.5-27B | 27B | INT4 | 9 tok/s | ~21.8s | |
#111 | MiMo V2 Flash | 15B (309B active) | INT4 | 1 tok/s | ~220.2s | |
#112 | Phi-4 Reasoning Plus | 14B | INT4 | 14 tok/s | ~9.8s | |
#117 | Gemma 4 26B A4B | 25.2B (3.8B active) | INT4 | 51 tok/s | ~3.6s | |
#125 | Qwen3.5-9B | 9B | INT4 Q8 | 29 tok/s 17 tok/s | ~6.3s ~6.3s | |
#128 | K2 Horizon 7B | 7B | INT4 Q8 FP16 | 37 tok/s 21 tok/s 10 tok/s | ~4.9s ~5.0s ~5.9s | |
#135 | Gemma 4 12B | 11.95B | INT4 Q8 | 16 tok/s 9 tok/s | ~8.3s ~9.9s | |
#140 | Qwen3.5-4B | 4B | INT4 Q8 FP16 | 61 tok/s 36 tok/s 19 tok/s | ~2.9s ~2.9s ~2.9s | |
#143 | GPT-OSS 20B | 21B (3.6B active) | INT4 | 20 tok/s | ~3.7s | |
#144 | GLM-4V | 9B | INT4 Q8 | 20 tok/s 13 tok/s | ~6.3s ~6.9s | |
#150 | NVIDIA Nemotron 3 Nano 30B-A3B | 3.5B (30B active) | INT4 Q8 FP16 | 9 tok/s 5 tok/s 3 tok/s | ~19.9s ~20.0s ~20.1s | |
#158 | Granite 4.2 8B | 8B | INT4 Q8 | 33 tok/s 19 tok/s | ~5.6s ~5.6s | |
#159 | Gemma 4 E4B | 8B | INT4 Q8 | 33 tok/s 19 tok/s | ~5.6s ~5.6s | |
#166 | Phi-4 | 14B | INT4 Q8 | 19 tok/s 10 tok/s | ~9.7s ~11.5s | |
#167 | Gemma 3 27B | 27B | INT4 | 9 tok/s | ~21.8s | |
#178 | OLMo 3 7B Think | 7B | INT4 Q8 | 25 tok/s 17 tok/s | ~4.9s ~5.0s | |
#179 | DeepSeek-R1 14B | 14B | INT4 Q8 | 20 tok/s 10 tok/s | ~9.7s ~11.5s | |
#183 | Ministral 3 14B | 14B | INT4 | 14 tok/s | ~9.8s | |
#186 | Gemma 3 12B | 12B | INT4 Q8 | 22 tok/s 12 tok/s | ~8.4s ~9.1s | |
#188 | Mistral-Small-2501 | 24B | INT4 | 11 tok/s | ~17.9s | |
#189 | Ministral 3 8B | 8B | INT4 Q8 | 23 tok/s 15 tok/s | ~5.6s ~5.6s | |
#191 | MiniCPM5-2B | 2B | INT4 Q8 FP16 | 106 tok/s 66 tok/s 36 tok/s | ~1.5s ~1.5s ~1.5s | |
#192 | Qwen3.5-2B | 2B | INT4 Q8 FP16 | 106 tok/s 66 tok/s 36 tok/s | ~1.5s ~1.5s ~1.5s | |
#193 | Gemma 2 27B | 27B | INT4 | 9 tok/s | ~21.8s | |
#194 | Qwen2.5-14B | 14B | INT4 Q8 | 19 tok/s 10 tok/s | ~9.7s ~11.5s | |
#200 | Gemma 4 E2B | 5.1B | INT4 Q8 FP16 | 49 tok/s 29 tok/s 15 tok/s | ~3.6s ~3.6s ~3.7s | |
#202 | DeepSeek-R1 8B | 8B | INT4 Q8 | 34 tok/s 19 tok/s | ~5.6s ~5.6s | |
#204 | Qwen3-4B | 4B | INT4 Q8 FP16 | 61 tok/s 36 tok/s 19 tok/s | ~2.9s ~2.9s ~2.9s | |
#205 | Ministral 3 3B | 3B | INT4 Q8 FP16 | 46 tok/s 34 tok/s 21 tok/s | ~2.2s ~2.2s ~2.2s | |
#207 | Gemma 2 9B | 9B | INT4 Q8 | 29 tok/s 17 tok/s | ~6.3s ~6.3s | |
#208 | Qwen3.5-0.8B | 0.8B | INT4 Q8 FP16 | 213 tok/s 144 tok/s 84 tok/s | ~620 ms ~622 ms ~627 ms | |
#209 | Qwen3-14B | 14B | INT4 Q8 | 19 tok/s 10 tok/s | ~9.7s ~11.5s | |
#210 | Gemma 3 4B | 4B | INT4 Q8 FP16 | 61 tok/s 36 tok/s 19 tok/s | ~2.9s ~2.9s ~2.9s | |
#211 | Qwen3-8B | 8B | INT4 Q8 | 33 tok/s 19 tok/s | ~5.6s ~5.6s | |
#213 | DeepSeek-R1 7B | 7B | INT4 Q8 FP16 | 38 tok/s 22 tok/s 11 tok/s | ~4.9s ~4.9s ~5.4s | |
#214 | Qwen3-1.7B | 1.7B | INT4 Q8 FP16 | 121 tok/s 77 tok/s 42 tok/s | ~1.3s ~1.3s ~1.3s | |
#215 | Llama 3.1 8B | 8B | INT4 Q8 | 33 tok/s 19 tok/s | ~5.6s ~5.6s | |
#216 | Gemma 3 270M | 0.27B | INT4 Q8 FP16 | 299 tok/s 247 tok/s 175 tok/s | ~203 ms ~204 ms ~205 ms | |
#218 | Qwen3-0.6B | 0.6B | INT4 Q8 FP16 | 259 tok/s 180 tok/s 108 tok/s | ~457 ms ~459 ms ~463 ms | |
#219 | Llama 3 8B | 8B | INT4 Q8 | 33 tok/s 19 tok/s | ~5.6s ~5.6s | |
#221 | Phi-4-Mini | 3.8B | INT4 Q8 FP16 | 63 tok/s 38 tok/s 20 tok/s | ~2.8s ~2.8s ~2.8s | |
#223 | Qwen2.5-7B | 7B | INT4 Q8 FP16 | 37 tok/s 21 tok/s 10 tok/s | ~4.9s ~5.0s ~5.9s | |
#224 | Ministral-8B-2410 | 8B | INT4 Q8 | 33 tok/s 19 tok/s | ~5.6s ~5.6s | |
#225 | DeepSeek-R1 1.5B | 1.5B | INT4 Q8 FP16 | 133 tok/s 85 tok/s 47 tok/s | ~1.2s ~1.2s ~1.2s | |
#226 | Llama 3.2 3B | 3B | INT4 Q8 FP16 | 77 tok/s 47 tok/s 25 tok/s | ~2.2s ~2.2s ~2.2s | |
#228 | Phi-3-mini | 3.8B | INT4 Q8 FP16 | 63 tok/s 38 tok/s 20 tok/s | ~2.8s ~2.8s ~2.8s | |
#229 | Gemma 3n E2B IT | 6B (2B active) | INT4 Q8 FP16 | 46 tok/s 38 tok/s 24 tok/s | ~1.6s ~1.7s ~1.8s | |
#230 | Mistral-7B-Instruct-v0.1 | 7.3B | INT4 Q8 FP16 | 36 tok/s 20 tok/s 10 tok/s | ~5.1s ~5.2s ~6.1s | |
#231 | Llama 3.2 1B | 1B | INT4 Q8 FP16 | 179 tok/s 119 tok/s 68 tok/s | ~789 ms ~792 ms ~798 ms | |
#232 | Gemma 2 2B | 2B | INT4 Q8 FP16 | 106 tok/s 66 tok/s 36 tok/s | ~1.5s ~1.5s ~1.5s | |
#233 | Phi-3-medium | 14B | INT4 Q8 | 19 tok/s 10 tok/s | ~9.7s ~11.5s | |
#234 | OLMo 3 7B Instruct | 7B | INT4 Q8 | 25 tok/s 17 tok/s | ~4.9s ~5.0s | |
#236 | Qwen2-7B | 7B | INT4 Q8 FP16 | 37 tok/s 21 tok/s 10 tok/s | ~4.9s ~5.0s ~5.9s | |
#237 | Phi-3-small | 7B | INT4 Q8 FP16 | 37 tok/s 21 tok/s 10 tok/s | ~4.9s ~5.0s ~5.9s | |
#238 | Gemma 3 1B | 1B | INT4 Q8 FP16 | 179 tok/s 119 tok/s 68 tok/s | ~789 ms ~792 ms ~798 ms | |
#239 | Mistral-7B-Instruct-v0.2 | 7.3B | INT4 Q8 FP16 | 36 tok/s 20 tok/s 10 tok/s | ~5.1s ~5.2s ~6.1s | |
#241 | Gemma 1 7B | 7B | INT4 Q8 | 25 tok/s 17 tok/s | ~4.9s ~5.0s | |
#242 | Gemma 1 2B | 2B | INT4 Q8 FP16 | 117 tok/s 70 tok/s 37 tok/s | ~1.5s ~1.5s ~1.5s | |
#243 | ChatGLM3-6B | 6B | INT4 Q8 FP16 | 28 tok/s 19 tok/s 11 tok/s | ~4.3s ~4.3s ~4.7s | |
#244 | ChatGLM2-6B | 6B | INT4 Q8 FP16 | 28 tok/s 19 tok/s 11 tok/s | ~4.3s ~4.3s ~4.7s | |
#245 | ChatGLM-6B | 6B | INT4 Q8 FP16 | 28 tok/s 19 tok/s 11 tok/s | ~4.3s ~4.3s ~4.7s | |
Unranked Models (Sorted by Speed) | ||||||
- | DINOv3 ViT-L/16 | 0.3B | INT4 Q8 FP16 | 377 tok/s 286 tok/s 186 tok/s | ~226 ms ~226 ms ~228 ms | |
- | Qwen2-0.5B | 0.5B | INT4 Q8 FP16 | 290 tok/s 206 tok/s 125 tok/s | ~378 ms ~380 ms ~383 ms | |
- | Qwen2.5-0.5B | 0.5B | INT4 Q8 FP16 | 290 tok/s 206 tok/s 125 tok/s | ~378 ms ~380 ms ~383 ms | |
- | ERNIE-4.5-0.3B | 0.3B | INT4 Q8 FP16 | 278 tok/s 229 tok/s 160 tok/s | ~227 ms ~227 ms ~229 ms | |
- | ERNIE-4.5-0.3B-Base | 0.3B | INT4 Q8 FP16 | 278 tok/s 229 tok/s 160 tok/s | ~227 ms ~227 ms ~229 ms | |
- | Liquid D1-Omni 600M | 0.6B | INT4 Q8 FP16 | 259 tok/s 180 tok/s 108 tok/s | ~457 ms ~459 ms ~463 ms | |
- | PixArt-α XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 257 tok/s 178 tok/s 106 tok/s | ~464 ms ~466 ms ~470 ms | |
- | PixArt-Σ XL 2 1024-MS | 0.61B | INT4 Q8 FP16 | 257 tok/s 178 tok/s 106 tok/s | ~464 ms ~466 ms ~470 ms | |
- | Nemotron 3.5 Parse | 0.63B | INT4 Q8 FP16 | 251 tok/s 174 tok/s 103 tok/s | ~483 ms ~484 ms ~488 ms | |
- | SD 2.1 Turbo | 0.86B | INT4 Q8 FP16 | 202 tok/s 136 tok/s 78 tok/s | ~669 ms ~671 ms ~676 ms | |
- | Stable Diffusion 1.4 | 0.86B | INT4 Q8 FP16 | 202 tok/s 136 tok/s 78 tok/s | ~669 ms ~671 ms ~676 ms | |
- | Stable Diffusion 2.1 | 0.86B | INT4 Q8 FP16 | 202 tok/s 136 tok/s 78 tok/s | ~669 ms ~671 ms ~676 ms | |
- | Falcon-1B | 1B | INT4 Q8 FP16 | 198 tok/s 127 tok/s 71 tok/s | ~788 ms ~791 ms ~797 ms | |
- | Falcon3-1B | 1B | INT4 Q8 FP16 | 179 tok/s 119 tok/s 68 tok/s | ~789 ms ~792 ms ~798 ms | |
- | MiniCPM-V 4.7 1B | 1B | INT4 Q8 FP16 | 179 tok/s 119 tok/s 68 tok/s | ~789 ms ~792 ms ~798 ms | |
- | Kandinsky 2.2 Decoder | 1.22B | INT4 Q8 FP16 | 156 tok/s 102 tok/s 57 tok/s | ~951 ms ~955 ms ~962 ms | |
- | Wan 2.1 T2V 1.3B | 1.3B | INT4 Q8 FP16 | 149 tok/s 97 tok/s 54 tok/s | ~1.0s ~1.0s ~1.0s | |
- | Qwen2-1.5B | 1.5B | INT4 Q8 FP16 | 133 tok/s 85 tok/s 47 tok/s | ~1.2s ~1.2s ~1.2s | |
- | Qwen2.5-1.5B | 1.5B | INT4 Q8 FP16 | 133 tok/s 85 tok/s 47 tok/s | ~1.2s ~1.2s ~1.2s | |
- | SVD Image-to-Video XT | 1.5B | INT4 Q8 FP16 | 133 tok/s 85 tok/s 47 tok/s | ~1.2s ~1.2s ~1.2s | |
- | SVD Image-to-Video XT 1.1 | 1.5B | INT4 Q8 FP16 | 133 tok/s 85 tok/s 47 tok/s | ~1.2s ~1.2s ~1.2s | |
- | LFM3 1.7B | 1.7B | INT4 Q8 FP16 | 121 tok/s 77 tok/s 42 tok/s | ~1.3s ~1.3s ~1.3s | |
- | LFM3 1.7B Base | 1.7B | INT4 Q8 FP16 | 121 tok/s 77 tok/s 42 tok/s | ~1.3s ~1.3s ~1.3s | |
- | Spark X2.5 1.7B | 1.7B | INT4 Q8 FP16 | 121 tok/s 77 tok/s 42 tok/s | ~1.3s ~1.3s ~1.3s | |
- | Hy-MT2 1.8B | 1.8B | INT4 Q8 FP16 | 116 tok/s 73 tok/s 40 tok/s | ~1.4s ~1.4s ~1.4s | |
- | CogVideoX 2B | 2B | INT4 Q8 FP16 | 106 tok/s 66 tok/s 36 tok/s | ~1.5s ~1.5s ~1.5s | |
- | LFM3 Audio 2B | 2B | INT4 Q8 FP16 | 106 tok/s 66 tok/s 36 tok/s | ~1.5s ~1.5s ~1.5s | |
- | LFM3 Omni 2B | 2B | INT4 Q8 FP16 | 106 tok/s 66 tok/s 36 tok/s | ~1.5s ~1.5s ~1.5s | |
- | LFM3 VL 2B | 2B | INT4 Q8 FP16 | 106 tok/s 66 tok/s 36 tok/s | ~1.5s ~1.5s ~1.5s | |
- | Liquid D1 2B | 2B | INT4 Q8 FP16 | 106 tok/s 66 tok/s 36 tok/s | ~1.5s ~1.5s ~1.5s | |
- | LTX-Video 0.9.1 | 2B | INT4 Q8 FP16 | 106 tok/s 66 tok/s 36 tok/s | ~1.5s ~1.5s ~1.5s | |
- | Moondream 3.1 | 9B (2B active) | INT4 Q8 | 106 tok/s 67 tok/s | ~1.7s ~1.7s | |
- | Stable Diffusion 3 Medium | 2B | INT4 Q8 FP16 | 106 tok/s 66 tok/s 36 tok/s | ~1.5s ~1.5s ~1.5s | |
- | Kandinsky 3.0 | 2.1B | INT4 Q8 FP16 | 102 tok/s 64 tok/s 35 tok/s | ~1.6s ~1.6s ~1.6s | |
- | LTX-2 | 2.2B | INT4 Q8 FP16 | 99 tok/s 61 tok/s 33 tok/s | ~1.7s ~1.7s ~1.7s | |
- | SDXL 1.0 Refiner | 2.31B | INT4 Q8 FP16 | 95 tok/s 59 tok/s 32 tok/s | ~1.7s ~1.7s ~1.8s | |
- | Stable Diffusion 3.5 Medium | 2.5B | INT4 Q8 FP16 | 89 tok/s 55 tok/s 30 tok/s | ~1.9s ~1.9s ~1.9s | |
- | SDXL 1.0 Base | 2.56B | INT4 Q8 FP16 | 88 tok/s 54 tok/s 29 tok/s | ~1.9s ~1.9s ~1.9s | |
- | SDXL Turbo | 2.56B | INT4 Q8 FP16 | 88 tok/s 54 tok/s 29 tok/s | ~1.9s ~1.9s ~1.9s | |
- | Falcon-3B | 3B | INT4 Q8 FP16 | 83 tok/s 49 tok/s 25 tok/s | ~2.2s ~2.2s ~2.2s | |
- | CroissantLLM Base | 1.3B | INT4 Q8 FP16 | 81 tok/s 65 tok/s 42 tok/s | ~1.0s ~1.0s ~1.0s | |
- | Phi-1 | 1.3B | INT4 Q8 FP16 | 81 tok/s 65 tok/s 42 tok/s | ~1.0s ~1.0s ~1.0s | |
- | Phi-1.5 | 1.3B | INT4 Q8 FP16 | 81 tok/s 65 tok/s 42 tok/s | ~1.0s ~1.0s ~1.0s | |
- | DeepSeek-R1 3B | 3B | INT4 Q8 FP16 | 79 tok/s 47 tok/s 25 tok/s | ~2.2s ~2.2s ~2.2s | |
- | Mellum 2.1 12B A2.5B Thinking | 12B (2.5B active) | INT4 Q8 | 79 tok/s 48 tok/s | ~2.2s ~2.3s | |
- | Falcon3-3B | 3B | INT4 Q8 FP16 | 77 tok/s 47 tok/s 25 tok/s | ~2.2s ~2.2s ~2.2s | |
- | LFM2-VL 3B | 3B | INT4 Q8 FP16 | 77 tok/s 47 tok/s 25 tok/s | ~2.2s ~2.2s ~2.2s | |
- | Liquid D1 3B | 3B | INT4 Q8 FP16 | 77 tok/s 47 tok/s 25 tok/s | ~2.2s ~2.2s ~2.2s | |
- | Liquid D1-VL 3B | 3B | INT4 Q8 FP16 | 77 tok/s 47 tok/s 25 tok/s | ~2.2s ~2.2s ~2.2s | |
- | Liquid LFM2-VL 3B D1 | 3B | INT4 Q8 FP16 | 77 tok/s 47 tok/s 25 tok/s | ~2.2s ~2.2s ~2.2s | |
- | Qwen2.5-3B | 3B | INT4 Q8 FP16 | 77 tok/s 47 tok/s 25 tok/s | ~2.2s ~2.2s ~2.2s | |
- | LFM2.5 24B A2B | 24B (2.5B active) | INT4 | 67 tok/s | ~2.7s | |
- | ERNIE-4.5-21B-A3B | 21B (3B active) | INT4 | 61 tok/s | ~2.9s | |
- | ERNIE-4.5-21B-A3B-Base | 21B (3B active) | INT4 | 61 tok/s | ~2.9s | |
- | FLUX.2 Klein 4B | 4B | INT4 Q8 FP16 | 61 tok/s 36 tok/s 19 tok/s | ~2.9s ~2.9s ~2.9s | |
- | FrogNano 4B | 4B | INT4 Q8 FP16 | 61 tok/s 36 tok/s 19 tok/s | ~2.9s ~2.9s ~2.9s | |
- | Mage-VL Cowork | 4B | INT4 Q8 FP16 | 61 tok/s 36 tok/s 19 tok/s | ~2.9s ~2.9s ~2.9s | |
- | Spark X2.5 4B | 4B | INT4 Q8 FP16 | 61 tok/s 36 tok/s 19 tok/s | ~2.9s ~2.9s ~2.9s | |
- | EmbeddingGemma 2 | 2B | INT4 Q8 FP16 | 57 tok/s 45 tok/s 29 tok/s | ~1.5s ~1.5s ~1.6s | |
- | ERNIE-4.5-VL-28B-A3B | 28B (3B active) | INT4 | 55 tok/s | ~3.3s | |
- | ERNIE-4.5-VL-28B-A3B-Base | 28B (3B active) | INT4 | 55 tok/s | ~3.3s | |
- | CogVideoX 1.5 5B | 5B | INT4 Q8 FP16 | 50 tok/s 29 tok/s 15 tok/s | ~3.6s ~3.6s ~3.6s | |
- | CogVideoX 5B | 5B | INT4 Q8 FP16 | 50 tok/s 29 tok/s 15 tok/s | ~3.6s ~3.6s ~3.6s | |
- | Wan 2.2 TI2V 5B | 5B | INT4 Q8 FP16 | 50 tok/s 29 tok/s 15 tok/s | ~3.6s ~3.6s ~3.6s | |
- | Phi-2 | 2.7B | INT4 Q8 FP16 | 49 tok/s 37 tok/s 23 tok/s | ~2.0s ~2.0s ~2.0s | |
- | MaLLaM-3B | 3B | INT4 Q8 FP16 | 46 tok/s 34 tok/s 21 tok/s | ~2.2s ~2.2s ~2.2s | |
- | SmolLM3 3B | 3B | INT4 Q8 FP16 | 46 tok/s 34 tok/s 21 tok/s | ~2.2s ~2.2s ~2.2s | |
- | Falcon-7B | 7B | INT4 Q8 FP16 | 39 tok/s 22 tok/s 11 tok/s | ~4.9s ~4.9s ~5.4s | |
- | AuraFlow v0.2 | 6.8B | INT4 Q8 FP16 | 38 tok/s 22 tok/s 11 tok/s | ~4.8s ~4.8s ~5.3s | |
- | AuraFlow v0.3 | 6.8B | INT4 Q8 FP16 | 38 tok/s 22 tok/s 11 tok/s | ~4.8s ~4.8s ~5.3s | |
- | Falcon3-7B | 7B | INT4 Q8 FP16 | 37 tok/s 21 tok/s 10 tok/s | ~4.9s ~5.0s ~5.9s | |
- | Hy-MT2 7B | 7B | INT4 Q8 FP16 | 37 tok/s 21 tok/s 10 tok/s | ~4.9s ~5.0s ~5.9s | |
- | Mistral-7B-v0.1 | 7.3B | INT4 Q8 FP16 | 36 tok/s 20 tok/s 10 tok/s | ~5.1s ~5.2s ~6.1s | |
- | Youtu Parsing Omni | 8B | INT4 Q8 | 34 tok/s 19 tok/s | ~5.6s ~5.6s | |
- | Stable Diffusion 3.5 Large | 8.1B | INT4 Q8 | 32 tok/s 19 tok/s | ~5.7s ~5.7s | |
- | Stable Diffusion 3.5 Large Turbo | 8.1B | INT4 Q8 | 32 tok/s 19 tok/s | ~5.7s ~5.7s | |
- | FLUX.2 Klein 9B | 9B | INT4 Q8 | 29 tok/s 17 tok/s | ~6.3s ~6.3s | |
- | LensVLM 9B | 9B | INT4 Q8 | 29 tok/s 17 tok/s | ~6.3s ~6.3s | |
- | MiMo V2.6 Distill Qwen 9B | 9B | INT4 Q8 | 29 tok/s 17 tok/s | ~6.3s ~6.3s | |
- | ChatGLM3-6B-32K | 6B | INT4 Q8 FP16 | 28 tok/s 19 tok/s 11 tok/s | ~4.3s ~4.3s ~4.7s | |
- | Yi-6B | 6B | INT4 Q8 FP16 | 28 tok/s 19 tok/s 11 tok/s | ~4.3s ~4.3s ~4.7s | |
- | Falcon3-10B | 10B | INT4 Q8 | 26 tok/s 15 tok/s | ~7.0s ~7.0s | |
- | Mochi 1 Preview | 10B | INT4 Q8 | 26 tok/s 15 tok/s | ~7.0s ~7.0s | |
- | Falcon2-11B | 11B | INT4 Q8 | 25 tok/s 14 tok/s | ~7.7s ~7.7s | |
- | Hunyuan Lite | 7B | INT4 Q8 | 25 tok/s 17 tok/s | ~4.9s ~5.0s | |
- | Kimi-VL-A3B-Instruct | 16B (3B active) | INT4 | 25 tok/s | ~2.8s | |
- | OLMo 3 7B Base | 7B | INT4 Q8 | 25 tok/s 17 tok/s | ~4.9s ~5.0s | |
- | SEA-LION-7B | 7.1B | INT4 Q8 | 25 tok/s 17 tok/s | ~5.0s ~5.0s | |
- | SEA-LION-7B-Instruct | 7.1B | INT4 Q8 | 25 tok/s 17 tok/s | ~5.0s ~5.0s | |
- | Sahabat-AI-Llama3-8B-Instruct | 8B | INT4 Q8 | 23 tok/s 15 tok/s | ~5.6s ~5.6s | |
- | Typhoon-2-8B | 8B | INT4 Q8 | 23 tok/s 15 tok/s | ~5.6s ~5.6s | |
- | FLUX.1 Canny Dev | 11.9B | INT4 Q8 | 22 tok/s 12 tok/s | ~8.3s ~9.1s | |
- | FLUX.1 Depth Dev | 11.9B | INT4 Q8 | 22 tok/s 12 tok/s | ~8.3s ~9.1s | |
- | FLUX.1 Dev | 11.9B | INT4 Q8 | 22 tok/s 12 tok/s | ~8.3s ~9.1s | |
- | FLUX.1 Fill Dev | 11.9B | INT4 Q8 | 22 tok/s 12 tok/s | ~8.3s ~9.1s | |
- | FLUX.1 Schnell | 11.9B | INT4 Q8 | 22 tok/s 12 tok/s | ~8.3s ~9.1s | |
- | HunyuanVideo 1.5 720P T2V | 13B | INT4 Q8 | 21 tok/s 11 tok/s | ~9.0s ~9.9s | |
- | GLM-4-9B | 9B | INT4 Q8 | 20 tok/s 13 tok/s | ~6.3s ~6.9s | |
- | GLM-4-9B-Chat | 9B | INT4 Q8 | 20 tok/s 13 tok/s | ~6.3s ~6.9s | |
- | GLM-4-9B-Chat-1M | 9B | INT4 Q8 | 20 tok/s 13 tok/s | ~6.3s ~6.9s | |
- | Sahabat-AI-Gemma2-9B | 9.2B | INT4 Q8 | 20 tok/s 13 tok/s | ~6.5s ~7.0s | |
- | Sahabat-AI-Gemma2-9B-Instruct | 9.2B | INT4 Q8 | 20 tok/s 13 tok/s | ~6.5s ~7.0s | |
- | Yi-9B | 9B | INT4 Q8 | 20 tok/s 13 tok/s | ~6.3s ~6.9s | |
- | Wan 2.1 I2V 14B 720P | 14B | INT4 Q8 | 19 tok/s 10 tok/s | ~9.7s ~11.5s | |
- | Wan 2.1 T2V 14B | 14B | INT4 Q8 | 19 tok/s 10 tok/s | ~9.7s ~11.5s | |
- | Wan 2.2 T2V A14B | 14B | INT4 Q8 | 19 tok/s 10 tok/s | ~9.7s ~11.5s | |
- | FLUX.2 Dev | 15B | INT4 Q8 | 18 tok/s 9 tok/s | ~10.4s ~12.3s | |
- | GreenMind-14B-R1 | 14B | INT4 | 14 tok/s | ~9.8s | |
- | Arete 27B | 27B | INT4 | 9 tok/s | ~21.8s | |
- | AREX-2 | 27B | INT4 | 9 tok/s | ~21.8s | |
- | PPLX Decider v1 27B | 27B | INT4 | 9 tok/s | ~21.8s | |
- | PPLX Decider v1.1 27B | 27B | INT4 | 9 tok/s | ~21.8s | |
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 A2 (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 200 GB/s aggregate bandwidth, batch size 1 inference operates in a memory-bandwidth bound regime. Generates approximately 44 tok/s on an 8B Q4 model and 5 tok/s on a 70B Q4 model.
Frequently Asked Questions
©2025 ApX Machine Learning