Can granite 3.1 3b a800m instruct run on the RX 7600?
Yes. At 8K context the best fit is Q8_0, using about 4.3 GB of the 7.6 GB usable on the RX 7600. Estimated speed ceiling: ~306 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 No | 867 |
| 3-bit (Q3_K_M) • | 2.2 GB Fits | 2.5 GB Fits | 4.0 GB Fits | 10.0 GB No | 668 |
| 4-bit (Q4_K_M) • | 2.6 GB Fits | 2.9 GB Fits | 4.4 GB Fits | 10.4 GB No | 534 |
| 5-bit (Q5_K_M) • | 2.9 GB Fits | 3.2 GB Fits | 4.7 GB Fits | 10.7 GB No | 457 |
| 6-bit (Q6_K) • | 3.3 GB Fits | 3.5 GB Fits | 5.0 GB Fits | 11.0 GB No | 396 |
| 8-bit (Q8_0) • | 4.0 GB Fits | 4.3 GB Fits | 5.8 GB Fits | 11.8 GB No | 306 |
| 16-bit (F16/BF16) • | 6.9 GB Tight | 7.1 GB Tight | 8.6 GB No | 14.6 GB No | 163 |
• real GGUF file size from bartowski/granite-3.1-3b-a800m-instruct-GGUF. Speed is a bandwidth ceiling (288 GB/s), not a benchmark. Methodology.
More
granite 3.1 3b a800m instruct on every GPU and Mac · Every model that runs on the RX 7600 · Other models that fit 8 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (ibm-granite/granite-3.1-3b-a800m-instruct), AMD specs. Data as of 2026-11-17.