▸ DEVICE UNDER TEST
NVIDIA Quadro 4000 Mac Edition — 2 GB VRAM.
▸ QUADRO 4000 MAC EDITION SPEC
- BRAND
- NVIDIA
- VRAM
- 2 GB GDDR5
- BANDWIDTH
- 89.9 GB/s
- FP16 COMPUTE
- 0.5 TFLOPS
- FP32 COMPUTE
- 0.5 TFLOPS
- CUDA CORES
- 256
- TDP
- 142 W
- ARCHITECTURE
- Fermi
▸ AI CAPABILITY
50/ 449 models @ Q4
With 2 GB VRAM and 89.9 GB/s bandwidth, this GPU handles models up to 1.71B parameters.
Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~10 tok/s.
§ 01TOP MODELS FOR QUADRO 4000 MAC EDITION
50 FIT · SHOWING 20| MODEL | SIZE | VRAM Q4 | TOK/S | AVG |
|---|---|---|---|---|
| SmolLM2 1.7B | 1.71B | 1.5 GB | 42 | 16.2 |
| Falcon3-1B | 1.67B | 1.5 GB | 43 | 42.0 |
| GPT-2 XL 1.5B | 1.61B | 1.5 GB | 45 | 5.1 |
| stablelm-2-1_6b | 1.6B | 1.5 GB | 45 | 9.5 |
| LFM2-VL 1.6B | 1.6B | 1.5 GB | 45 | 39.7 |
| Falcon-H1 1.5B | 1.55B | 1.4 GB | 46 | 43.8 |
| Qwen2.5-Coder-1.5B | 1.5B | 1.4 GB | 48 | 19.6 |
| Qwen2 Math 1.5B | 1.5B | 1.4 GB | 48 | 19.6 |
| Qwen 2.5 1.5B | 1.5B | 1.4 GB | 48 | 30.2 |
| Yi Coder 1.5B | 1.5B | 1.4 GB | 48 | 14.6 |
| Stella en 1.5B v5 | 1.5B | 1.4 GB | 48 | — |
| Phi-1 1.3B | 1.42B | 1.4 GB | 51 | 7.2 |
| Phi-1.5 1.3B | 1.42B | 1.4 GB | 51 | 7.2 |
| DeepSeek Coder 1.3B | 1.35B | 1.3 GB | 53 | 16.8 |
| EXAONE-4.0-1.2B | 1.3B | 1.3 GB | 55 | 18.9 |
| OPT 1.3B | 1.3B | 1.3 GB | 55 | 5.3 |
| MiniCPM-V 4.6 | 1.3B | 1.3 GB | 55 | 21.5 |
| LFM2.5-1.2B-Thinking | 1.2B | 1.2 GB | 60 | 19.6 |
| Llama-3.2-1B | 1.2B | 1.2 GB | 60 | 10.1 |
| LFM2 1.2B | 1.2B | 1.2 GB | 60 | 15.6 |