Phind-CodeLlama-34B-v2
by Phind
39.4B params · text-generation · 833 likes · 2.1k downloads
Phind-CodeLlama-34B-v2 is a 39.4B parameter model. At Q4 quantization it requires 20GB of VRAM. It runs comfortably on GeForce RTX 4090 (33 tok/s), GeForce RTX 5090 (49 tok/s), A100 PCIe 80 GB (61 tok/s).
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 33 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 49 tok/s | comfortable |
| M4 Max 128GB | 128GB | 12 tok/s | tight |
| M4 Pro 48GB | 48GB | 6 tok/s | tight |
| M4 Pro 24GB | 24GB | 6 tok/s | tight |
| A100 PCIe 80 GB | 80GB | 61 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 122 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 29 tok/s | tight |
| Radeon RX 7900 XTX | 24GB | 24 tok/s | tight |
| M4 Max 64GB | 64GB | 12 tok/s | tight |