Can granite 3.1 3b a800m instruct run on the RTX 4070 Super?
Yes. At 8K context the best fit is F16, using about 7.1 GB of the 11.4 GB usable on the RTX 4070 Super. Estimated speed ceiling: ~285 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) • | 1.9 GB Fits | 2.1 GB Fits | 3.6 GB Fits | 9.6 GB Fits | 1517 |
| 3-bit (Q3_K_M) • | 2.2 GB Fits | 2.5 GB Fits | 4.0 GB Fits | 10.0 GB Fits | 1169 |
| 4-bit (Q4_K_M) • | 2.6 GB Fits | 2.9 GB Fits | 4.4 GB Fits | 10.4 GB Tight | 934 |
| 5-bit (Q5_K_M) • | 2.9 GB Fits | 3.2 GB Fits | 4.7 GB Fits | 10.7 GB Tight | 800 |
| 6-bit (Q6_K) • | 3.3 GB Fits | 3.5 GB Fits | 5.0 GB Fits | 11.0 GB Tight | 694 |
| 8-bit (Q8_0) • | 4.0 GB Fits | 4.3 GB Fits | 5.8 GB Fits | 11.8 GB No | 536 |
| 16-bit (F16/BF16) • | 6.9 GB Fits | 7.1 GB Fits | 8.6 GB Fits | 14.6 GB No | 285 |
• real GGUF file size from bartowski/granite-3.1-3b-a800m-instruct-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.
More
granite 3.1 3b a800m instruct on every GPU and Mac · Every model that runs on the RTX 4070 Super · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (ibm-granite/granite-3.1-3b-a800m-instruct), NVIDIA specs. Data as of 2026-11-17.