Models › Beam-1.0-501B-A23B
Beam-1.0-501B-A23B: VRAM needs and speed by GPU
At UD-Q4_K_XL, Beam-1.0-501B-A23B needs about 309.5 GB of VRAM. No measured runs yet. Speeds below are estimates. Submit a run.
501.27B parameters (mixture-of-experts, ~23.0B active) · license: apache-2.0 · 1,048,576-token context · GGUF published Oct 16, 2026 · GGUF files on Hugging Face
Memory needed per quantization
| Quant | File size | Needs (estimate) | Smallest card it fits |
|---|---|---|---|
| UD-IQ1_S | 103.1 GB | 106.1 GB | multi-GPU / large unified memory |
| UD-IQ1_M | 123.6 GB | 126.6 GB | multi-GPU / large unified memory |
| UD-IQ2_XXS | 133.9 GB | 136.9 GB | multi-GPU / large unified memory |
| UD-IQ2_M | 164.8 GB | 167.8 GB | multi-GPU / large unified memory |
| UD-Q2_K_XL | 186.9 GB | 189.9 GB | multi-GPU / large unified memory |
| UD-IQ3_XXS | 197.2 GB | 200.2 GB | multi-GPU / large unified memory |
| UD-Q3_K_XL | 242.3 GB | 245.3 GB | multi-GPU / large unified memory |
| UD-Q4_K_XL | 306.5 GB | 309.5 GB | multi-GPU / large unified memory |
| UD-Q5_K_XL | 369.5 GB | 372.5 GB | multi-GPU / large unified memory |
| UD-Q6_K_XL | 453.2 GB | 456.2 GB | multi-GPU / large unified memory |
| Q8_0 | 532.8 GB | 535.8 GB | multi-GPU / large unified memory |
| BF16 | 1002.7 GB | 1005.7 GB | multi-GPU / large unified memory |
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 | Does not fit | |
| NVIDIA RTX 4090 | Does not fit | |
| NVIDIA RTX 5090 | Does not fit | |
| AMD Radeon RX 7900 XTX | Does not fit | |
| Apple M4 Pro (20-core GPU) | Does not fit | |
| Apple M3 Max (40-core GPU) | Does not fit | |
| AMD Ryzen AI Max+ 395 (Radeon 8060S) | Does not fit | |
Too big for your card?
Run Beam-1.0-501B-A23B 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.