Can GLiDE 27B run on the RTX 5090?
Yes. At 8K context the best fit is Q8_0, using about 27.2 GB of the 30.4 GB usable on the RTX 5090. Estimated speed ceiling: ~65 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) | 10.2 GB Fits | 10.5 GB Fits | 12.0 GB Fits | 18.0 GB Fits | 183 |
| 3-bit (Q3_K_M) | 13.0 GB Fits | 13.2 GB Fits | 14.7 GB Fits | 20.7 GB Fits | 141 |
| 4-bit (Q4_K_M) | 16.0 GB Fits | 16.2 GB Fits | 17.7 GB Fits | 23.7 GB Fits | 112 |
| 5-bit (Q5_K_M) | 18.4 GB Fits | 18.7 GB Fits | 20.2 GB Fits | 26.2 GB Fits | 96 |
| 6-bit (Q6_K) | 21.0 GB Fits | 21.3 GB Fits | 22.8 GB Fits | 28.8 GB Tight | 84 |
| 8-bit (Q8_0) | 26.9 GB Fits | 27.2 GB Fits | 28.7 GB Tight | 34.7 GB No | 65 |
| 16-bit (F16/BF16) | 49.7 GB No | 50.0 GB No | 51.5 GB No | 57.5 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (1792 GB/s), not a benchmark. Methodology.
More
GLiDE 27B on every GPU and Mac · Every model that runs on the RTX 5090 · Other models that fit 32 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (fastino/GLiDE-27B), NVIDIA specs. Data as of 2026-11-17.