Models › gemma-4-31B-it-qat-q4_0-unquantized
gemma-4-31B-it-qat-q4_0-unquantized: VRAM needs and speed by GPU
At UD-Q4_K_XL, gemma-4-31B-it-qat-q4_0-unquantized needs about 18.9 GB of VRAM. No measured runs yet. Speeds below are estimates. Submit a run.
30.7B parameters · license: apache-2.0 · 262,144-token context · GGUF published Jun 5, 2026 · GGUF files on Hugging Face
Memory needed per quantization
| Quant | File size | Needs (estimate) | Smallest card it fits |
|---|---|---|---|
| UD-Q4_K_XL | 17.3 GB | 18.9 GB | 24 GB cards |
Expected speed on popular hardware
| Hardware | Best quant that fits | Expected tok/s |
|---|---|---|
| NVIDIA RTX 3060 | Does not fit | |
| NVIDIA RTX 4060 Ti | Does not fit | |
| NVIDIA RTX 3090 | UD-Q4_K_XL | 37.9 estimate |
| NVIDIA RTX 4090 | UD-Q4_K_XL | 42.0 estimate |
| NVIDIA RTX 5090 | UD-Q4_K_XL | 66.4 estimate |
| AMD Radeon RX 7900 XTX | UD-Q4_K_XL | 42.2 estimate |
| Apple M4 Pro (20-core GPU) (64 GB) | UD-Q4_K_XL | 13.4 estimate |
| Apple M3 Max (40-core GPU) (64 GB) | UD-Q4_K_XL | 19.6 estimate |
| AMD Ryzen AI Max+ 395 (Radeon 8060S) | UD-Q4_K_XL | 12.0 estimate |
Too big for your card?
Run gemma-4-31B-it-qat-q4_0-unquantized on a rented 24-80 GB GPU by the hour.
Rent a bigger GPU on RunPodAffiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.