Models › DeepSeek-R1-0528-Qwen3-8B
DeepSeek-R1-0528-Qwen3-8B: VRAM needs and speed by GPU
At Q4_K_M, DeepSeek-R1-0528-Qwen3-8B needs about 6.0 GB of VRAM. No measured runs yet. Speeds below are estimates. Submit a run.
8.19B parameters · license: mit · 131,072-token context · GGUF published May 29, 2025 · GGUF files on Hugging Face
Memory needed per quantization
| Quant | File size | Needs (estimate) | Smallest card it fits |
|---|---|---|---|
| UD-IQ1_S | 2.3 GB | 3.3 GB | 8 GB cards |
| UD-IQ1_M | 2.4 GB | 3.4 GB | 8 GB cards |
| UD-IQ2_XXS | 2.6 GB | 3.6 GB | 8 GB cards |
| UD-IQ2_M | 3.1 GB | 4.1 GB | 8 GB cards |
| Q2_K | 3.3 GB | 4.3 GB | 8 GB cards |
| UD-IQ3_XXS | 3.4 GB | 4.4 GB | 8 GB cards |
| Q2_K_L | 3.4 GB | 4.4 GB | 8 GB cards |
| UD-Q2_K_XL | 3.5 GB | 4.5 GB | 8 GB cards |
| Q3_K_S | 3.8 GB | 4.8 GB | 8 GB cards |
| Q3_K_M | 4.1 GB | 5.1 GB | 8 GB cards |
| UD-Q3_K_XL | 4.3 GB | 5.3 GB | 8 GB cards |
| IQ4_XS | 4.6 GB | 5.6 GB | 8 GB cards |
| Q4_0 | 4.8 GB | 5.8 GB | 8 GB cards |
| IQ4_NL | 4.8 GB | 5.8 GB | 8 GB cards |
| Q4_K_S | 4.8 GB | 5.8 GB | 8 GB cards |
| Q4_K_M | 5.0 GB | 6.0 GB | 8 GB cards |
| UD-Q4_K_XL | 5.1 GB | 6.1 GB | 8 GB cards |
| Q4_1 | 5.2 GB | 6.2 GB | 8 GB cards |
| Q5_K_S | 5.7 GB | 6.7 GB | 8 GB cards |
| Q5_K_M | 5.9 GB | 6.9 GB | 8 GB cards |
| UD-Q5_K_XL | 5.9 GB | 6.9 GB | 8 GB cards |
| Q6_K | 6.7 GB | 7.7 GB | 12 GB cards |
| UD-Q6_K_XL | 7.5 GB | 8.5 GB | 12 GB cards |
| Q8_0 | 8.7 GB | 9.7 GB | 12 GB cards |
| UD-Q8_K_XL | 10.8 GB | 11.8 GB | 16 GB cards |
| BF16 | 16.4 GB | 17.4 GB | 24 GB cards |
Expected speed on popular hardware
| Hardware | Best quant that fits | Expected tok/s |
|---|---|---|
| NVIDIA RTX 3060 | Q8_0 | 35.4 estimate |
| NVIDIA RTX 4060 Ti | Q5_K_M | 41.8 estimate |
| NVIDIA RTX 3090 | Q8_0 | 75.3 estimate |
| NVIDIA RTX 4090 | Q8_0 | 83.4 estimate |
| NVIDIA RTX 5090 | Q8_0 | 132 estimate |
| AMD Radeon RX 7900 XTX | Q8_0 | 83.8 estimate |
| Apple M4 Pro (20-core GPU) (64 GB) | Q8_0 | 26.6 estimate |
| Apple M3 Max (40-core GPU) (64 GB) | Q8_0 | 38.8 estimate |
| AMD Ryzen AI Max+ 395 (Radeon 8060S) | Q8_0 | 23.9 estimate |
Too big for your card?
Run DeepSeek-R1-0528-Qwen3-8B 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.