Can Groot 19B A3B 261023 run on the RX 7900 GRE?
Yes. At 8K context the best fit is Q4_K_M, using about 12.7 GB of the 15.2 GB usable on the RX 7900 GRE. Estimated speed ceiling: ~299 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) • | 8.3 GB Fits | 8.4 GB Fits | 8.8 GB Fits | 10.7 GB Fits | 473 |
| 3-bit (Q3_K_M) • | 9.9 GB Fits | 10.0 GB Fits | 10.5 GB Fits | 12.3 GB Fits | 388 |
| 4-bit (Q4_K_M) • | 12.6 GB Fits | 12.7 GB Fits | 13.1 GB Fits | 15.0 GB Tight | 299 |
| 5-bit (Q5_K_M) • | 14.7 GB Tight | 14.7 GB Tight | 15.2 GB No | 17.1 GB No | 253 |
| 6-bit (Q6_K) • | 16.6 GB No | 16.7 GB No | 17.1 GB No | 19.0 GB No | — |
| 8-bit (Q8_0) • | 19.8 GB No | 19.9 GB No | 20.3 GB No | 22.2 GB No | — |
| 16-bit (F16/BF16) • | 36.3 GB No | 36.4 GB No | 36.9 GB No | 38.8 GB No | — |
• real GGUF file size from bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF. Speed is a bandwidth ceiling (576 GB/s), not a benchmark. Methodology.
More
Groot 19B A3B 261023 on every GPU and Mac · Every model that runs on the RX 7900 GRE · Other models that fit 16 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (GrootTeam/Groot-19B-A3B-261023), AMD specs. Data as of 2026-11-17.