NVIDIA RTX 5060 SUPER
GPURTX 5060 SUPER (rumored, CES 2026): 12GB VRAM, 128-bit bus. Entry-tier local inference; 7-13B Q4 smooth.
5
Run records
5
Models covered
2
Frameworks covered
L0 Self-reported × 5
Evidence mix
Typical measured performance
Published benchmark averages per model × framework × quantization on this hardware.
- llama.cpp · Q4_K_M Decode 71.3 · Prefill 534.8 ·
- llama.cpp · Q8_0 Decode 388.3 · Prefill 2912.3 ·
- llama.cpp · Q4_K_M Decode — · Prefill — ·
- llama.cpp · Q4_K_M Decode 145.6 · Prefill 1092 ·
- Strata · Q4_K_M Decode 186.7 · Prefill 1400.3 ·
Key specs
- Vendor
- NVIDIA
- Architecture
- Blackwell
- VRAM
- 12 GB
- Memory bandwidth
- 448 GB/s
- TDP
- 180 W
- Release date
- 2026-03-01
Run records
5 configurations
| Model | Framework | Quantization | Decode | Gen time | Samples |
|---|---|---|---|---|---|
| Ministral-3-8B-Instruct-2512 | llama.cpp | Q4_K_M | 71.3 tok/s | — | 1 |
| Qwen3.5-0.8B | llama.cpp | Q8_0 | 388.3 tok/s | — | 1 |
| gemma-4-E2B-it | llama.cpp | Q4_K_M | — | — | 1 |
| Qwen3-4B | llama.cpp | Q4_K_M | 145.6 tok/s | — | 1 |
| Qwen3.5-4B | Strata | Q4_K_M | 186.7 tok/s | — | 1 |