▸ DEVICE UNDER TEST
NVIDIA Quadro K200M — 2 GB VRAM.
▸ QUADRO K200M SPEC
- BRAND
- NVIDIA
- VRAM
- 2 GB DDR3
- BANDWIDTH
- 14 GB/s
- FP16 COMPUTE
- 0.3 TFLOPS
- FP32 COMPUTE
- 0.3 TFLOPS
- CUDA CORES
- 192
- TDP
- 35 W
- ARCHITECTURE
- Kepler
▸ AI CAPABILITY
42/ 331 models @ Q4
With 2 GB VRAM and 14 GB/s bandwidth, this GPU handles models up to 2B parameters.
Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~2 tok/s.
§ 01TOP MODELS FOR QUADRO K200M
42 FIT · SHOWING 20| MODEL | SIZE | VRAM Q4 | TOK/S | AVG |
|---|---|---|---|---|
| Gemma 1 2B | 2B | 1.7 GB | 6 | 20.2 |
| Granite 3.0 2B | 2B | 1.7 GB | 6 | 35.8 |
| Granite 3.1 2B | 2B | 1.7 GB | 6 | 37.8 |
| Granite 3.3 2B | 2B | 1.7 GB | 6 | 20.5 |
| Qwen 3.5 2B | 2B | 1.7 GB | 6 | 29.7 |
| Moondream2 1.9B | 1.9B | 1.6 GB | 6 | 26.2 |
| Qwen 1.5 1.8B | 1.8B | 1.6 GB | 6 | 19.6 |
| SmolLM2 1.7B | 1.71B | 1.5 GB | 7 | 16.2 |
| Qwen3 1.7B | 1.7B | 1.5 GB | 7 | 30.1 |
| stablelm-2-1_6b | 1.6B | 1.5 GB | 7 | 9.5 |
| Falcon-H1 1.5B | 1.5B | 1.4 GB | 7 | 43.8 |
| GPT-2 XL 1.5B | 1.5B | 1.4 GB | 7 | 5.1 |
| Qwen2.5-Coder-1.5B | 1.5B | 1.4 GB | 7 | 19.6 |
| Qwen2 Math 1.5B | 1.5B | 1.4 GB | 7 | 19.6 |
| Qwen 2.5 1.5B | 1.5B | 1.4 GB | 7 | 30.2 |
| Yi Coder 1.5B | 1.5B | 1.4 GB | 7 | 14.6 |
| DeepSeek Coder 1.3B | 1.3B | 1.3 GB | 9 | 16.8 |
| EXAONE-4.0-1.2B | 1.3B | 1.3 GB | 9 | 18.9 |
| OPT 1.3B | 1.3B | 1.3 GB | 9 | 5.3 |
| Phi-1 1.3B | 1.3B | 1.3 GB | 9 | 7.2 |