Quantization-specific throughput and VRAM requirements for codellama/CodeLlama-34b-hf running on NVIDIA H200 SXM 141GB.
Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.
For full verdict logic and alternate GPUs, see the canonical compatibility page.
Open full compatibility report| Quantization | VRAM needed | VRAM available | Speed | Verdict |
|---|---|---|---|---|
| Q4 | 17GB | 141GB | 263 tok/s | ✅ Fits |
| Q8 | 35GB | 141GB | 170 tok/s | ✅ Fits |
| FP16 | 70GB | 141GB | 88 tok/s | ✅ Fits |