NVIDIA RTX 4060
GPUAda Lovelace; 8GB VRAM, 272 GB/s bandwidth, 115W TDP, CUDA cores 3,072. Release date: 2023-06-29. Source: LCZ hardware catalog, with missing fields supplemented from NVIDIA official materials.
2
Run records
1
Models covered
1
Frameworks covered
L0 Self-reported × 2
Evidence mix
Typical measured performance
Published benchmark averages per model × framework × quantization on this hardware.
- llama.cpp · Q5_K_M Decode 70.7 · Prefill 530.3 ·
- llama.cpp · Q4_K_M Decode 88.4 · Prefill 663 ·
Key specs
- Vendor
- NVIDIA
- Architecture
- Ada Lovelace
- VRAM
- 8 GB
- Memory bandwidth
- 272 GB/s
- TDP
- 115 W
- Release date
- 2023-06-29
Run records
2 configurations
| Model | Framework | Quantization | Decode | Gen time | Samples |
|---|---|---|---|---|---|
| Qwen3.5-4B | llama.cpp | Q5_K_M | 70.7 tok/s | — | 1 |
| Qwen3.5-4B | llama.cpp | Q4_K_M | 88.4 tok/s | — | 1 |