Can Ling 3.0 tiny run on the RX 7900 GRE?
Yes. At 8K context the best fit is Q8_0, using about 8.7 GB of the 15.2 GB usable on the RX 7900 GRE. Estimated speed ceiling: ~391 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) • | 3.6 GB Fits | 3.7 GB Fits | 4.3 GB Fits | 6.9 GB Fits | 1097 |
| 3-bit (Q3_K_M) • | 4.3 GB Fits | 4.4 GB Fits | 5.1 GB Fits | 7.6 GB Fits | 869 |
| 4-bit (Q4_K_M) • | 5.4 GB Fits | 5.5 GB Fits | 6.1 GB Fits | 8.7 GB Fits | 669 |
| 5-bit (Q5_K_M) • | 6.1 GB Fits | 6.2 GB Fits | 6.9 GB Fits | 9.4 GB Fits | 576 |
| 6-bit (Q6_K) • | 7.2 GB Fits | 7.3 GB Fits | 7.9 GB Fits | 10.4 GB Fits | 481 |
| 8-bit (Q8_0) • | 8.6 GB Fits | 8.7 GB Fits | 9.4 GB Fits | 11.9 GB Fits | 391 |
| 16-bit (F16/BF16) • | 15.5 GB No | 15.6 GB No | 16.3 GB No | 18.8 GB No | — |
• real GGUF file size from bartowski/Ling-3.0-tiny-GGUF. Speed is a bandwidth ceiling (576 GB/s), not a benchmark. Methodology.
More
Ling 3.0 tiny 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 (inclusionAI/Ling-3.0-tiny), AMD specs. Data as of 2026-11-17.