Q4_K_M
342.5 GBMin VRAM: 393.9 GB
Recommended VRAM: 445.3 GB
Min RAM: 514 GB
Context: 8K / 8K
Loading model details...
Fetching variants, compatibility details, and metadata.
Loading model details...
Fetching variants, compatibility details, and metadata.
Share DeepSeek V3.2 with someone who is deciding what to run locally.
Social proof
0% of 981 scanned PCs run DeepSeek V3.2 fully on GPU.
191 keep at least some work on GPU. Based on anonymous compatibility checks.
General-purpose local model brief
Best for
Consider alternatives if
Quantization tip: Benchmark at least two quantizations and validate with a task-specific eval set before production use.
New to local models? Smaller quantization variants are easier to run, while larger ones can improve quality at the cost of more memory.
Q4_K_M
342.5 GBMin VRAM: 393.9 GB
Recommended VRAM: 445.3 GB
Min RAM: 514 GB
Context: 8K / 8K
Q5_K_M
428.1 GBMin VRAM: 492.3 GB
Recommended VRAM: 556.5 GB
Min RAM: 643 GB
Context: 8K / 8K
Q8_0
685 GBMin VRAM: 787.7 GB
Recommended VRAM: 890.5 GB
Min RAM: 1028 GB
Context: 8K / 8K
FP16
1370 GBMin VRAM: 1575.5 GB
Recommended VRAM: 1781 GB
Min RAM: 2055 GB
Context: 8K / 8K
| Quantization | File Size | Min VRAM | Recommended VRAM | Min RAM | Context |
|---|---|---|---|---|---|
| Q4_K_M | 342.5 GB | 393.9 GB | 445.3 GB | 514 GB | 8K / 8K |
| Q5_K_M | 428.1 GB | 492.3 GB | 556.5 GB | 643 GB | 8K / 8K |
| Q8_0 | 685 GB | 787.7 GB | 890.5 GB | 1028 GB | 8K / 8K |
| FP16 | 1370 GB | 1575.5 GB | 1781 GB | 2055 GB | 8K / 8K |