Can Yi 1.5 34B Chat run on the RTX 5070?
No. Even at 2-bit with 8K context, Yi 1.5 34B Chat needs about 14.3 GB, more than the 11.4 GB usable on the RTX 5070.
Memory by quant and context
| Quant | 4K ctx | Max tok/s (est., 8K) |
|---|---|---|
| 2-bit (Q2_K) • | 13.4 GB No | — |
| 3-bit (Q3_K_M) | 17.1 GB No | — |
| 4-bit (Q4_K_M) • | 20.7 GB No | — |
| 5-bit (Q5_K_M) • | 24.1 GB No | — |
| 6-bit (Q6_K) • | 27.7 GB No | — |
| 8-bit (Q8_0) • | 35.5 GB No | — |
| 16-bit (F16/BF16) | 65.5 GB No | — |
• real GGUF file size from lmstudio-community/Yi-1.5-34B-Chat-GGUF. Speed is a bandwidth ceiling (672 GB/s), not a benchmark. Methodology.
Hardware that does fit it
RTX 4060 Ti 16GBRTX 4070 Ti SuperRTX 4080RTX 4080 SuperRTX 5060 Ti 16GBRTX 5070 Ti
More
Yi 1.5 34B Chat on every GPU and Mac · Every model that runs on the RTX 5070 · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (01-ai/Yi-1.5-34B-Chat), NVIDIA specs. Data as of 2026-11-17.