Q3_K_M
21 GBMin VRAM: 23 GB
Recommended VRAM: 28 GB
Min RAM: 28 GB
Context: 4K / 32K
Loading model details...
Fetching variants, compatibility details, and metadata.
New to local models? Smaller quantization variants are easier to run, while larger ones can improve quality at the cost of more memory.
Q3_K_M
21 GBMin VRAM: 23 GB
Recommended VRAM: 28 GB
Min RAM: 28 GB
Context: 4K / 32K
Q4_K_M
26 GBMin VRAM: 28 GB
Recommended VRAM: 48 GB
Min RAM: 32 GB
Context: 4K / 32K
Q5_K_M
32 GBMin VRAM: 34 GB
Recommended VRAM: 48 GB
Min RAM: 40 GB
Context: 4K / 32K
| Quantization | File Size | Min VRAM | Recommended VRAM | Min RAM | Context |
|---|---|---|---|---|---|
| Q3_K_M | 21 GB | 23 GB | 28 GB | 28 GB | 4K / 32K |
| Q4_K_M | 26 GB | 28 GB | 48 GB | 32 GB | 4K / 32K |
| Q5_K_M | 32 GB | 34 GB | 48 GB | 40 GB | 4K / 32K |