Can Llama 3.2 3B Instruct run on the RTX 4080 Super?
Yes. At 8K context the best fit is F16, using about 13.5 GB of the 15.2 GB usable on the RTX 4080 Super. Estimated speed ceiling: ~57 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 | 540 |
| 3-bit (Q3_K_M) • | 2.7 GB Fits | 3.1 GB Fits | 5.7 GB Fits | 16.2 GB No | 436 |
| 4-bit (Q4_K_M) • | 3.0 GB Fits | 3.4 GB Fits | 6.0 GB Fits | 16.5 GB No | 364 |
| 5-bit (Q5_K_M) • | 3.2 GB Fits | 3.7 GB Fits | 6.3 GB Fits | 16.8 GB No | 317 |
| 6-bit (Q6_K) • | 3.5 GB Fits | 4.0 GB Fits | 6.6 GB Fits | 17.1 GB No | 278 |
| 8-bit (Q8_0) • | 4.3 GB Fits | 4.7 GB Fits | 7.3 GB Fits | 17.8 GB No | 215 |
| 16-bit (F16/BF16) • | 13.1 GB Fits | 13.5 GB Fits | 16.1 GB No | 26.6 GB No | 57 |
• real GGUF file size from unsloth/Llama-3.2-3B-Instruct-GGUF. Speed is a bandwidth ceiling (736 GB/s), not a benchmark. Methodology.
More
Llama 3.2 3B Instruct on every GPU and Mac · Every model that runs on the RTX 4080 Super · Other models that fit 16 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (meta-llama/Llama-3.2-3B-Instruct), NVIDIA specs. Data as of 2026-11-17.