Can Hermes 3 Llama 3.2 3B run on the RTX 5070 Ti?
Yes. At 8K context the best fit is F16, using about 7.5 GB of the 15.2 GB usable on the RTX 5070 Ti. Estimated speed ceiling: ~139 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 2.4 GB Fits | 2.8 GB Fits | 5.4 GB Fits | 15.9 GB No | 657 |
| 3-bit (Q3_K_M) • | 2.7 GB Fits | 3.1 GB Fits | 5.7 GB Fits | 16.2 GB No | 531 |
| 4-bit (Q4_K_M) • | 3.0 GB Fits | 3.4 GB Fits | 6.0 GB Fits | 16.5 GB No | 444 |
| 5-bit (Q5_K_M) • | 3.2 GB Fits | 3.7 GB Fits | 6.3 GB Fits | 16.8 GB No | 386 |
| 6-bit (Q6_K) • | 3.5 GB Fits | 4.0 GB Fits | 6.6 GB Fits | 17.1 GB No | 339 |
| 8-bit (Q8_0) • | 4.3 GB Fits | 4.7 GB Fits | 7.3 GB Fits | 17.8 GB No | 262 |
| 16-bit (F16/BF16) • | 7.1 GB Fits | 7.5 GB Fits | 10.1 GB Fits | 20.6 GB No | 139 |
• real GGUF file size from bartowski/Hermes-3-Llama-3.2-3B-GGUF. Speed is a bandwidth ceiling (896 GB/s), not a benchmark. Methodology.
More
Hermes 3 Llama 3.2 3B on every GPU and Mac · Every model that runs on the RTX 5070 Ti · Other models that fit 16 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (NousResearch/Hermes-3-Llama-3.2-3B), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.