Q4_K_M
337.5 GBMin VRAM: 388.1 GB
Recommended VRAM: 438.8 GB
Min RAM: 507 GB
Context: 8K / 8K
Loading model details...
Fetching variants, compatibility details, and metadata.
Loading model details...
Fetching variants, compatibility details, and metadata.
Model Detail
Share Mistral Large 3 675B with someone who is deciding what to run locally.
Social proof
0% of 982 scanned PCs run Mistral Large 3 675B fully on GPU.
201 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
337.5 GBMin VRAM: 388.1 GB
Recommended VRAM: 438.8 GB
Min RAM: 507 GB
Context: 8K / 8K
Q5_K_M
421.9 GBMin VRAM: 485.2 GB
Recommended VRAM: 548.5 GB
Min RAM: 633 GB
Context: 8K / 8K
Q8_0
675 GBMin VRAM: 776.2 GB
Recommended VRAM: 877.5 GB
Min RAM: 1013 GB
Context: 8K / 8K
FP16
1350 GBMin VRAM: 1552.5 GB
Recommended VRAM: 1755 GB
Min RAM: 2025 GB
Context: 8K / 8K
| Quantization | File Size | Min VRAM | Recommended VRAM | Min RAM | Context |
|---|---|---|---|---|---|
| Q4_K_M | 337.5 GB | 388.1 GB | 438.8 GB | 507 GB | 8K / 8K |
| Q5_K_M | 421.9 GB | 485.2 GB | 548.5 GB | 633 GB | 8K / 8K |
| Q8_0 | 675 GB | 776.2 GB | 877.5 GB | 1013 GB | 8K / 8K |
| FP16 | 1350 GB | 1552.5 GB | 1755 GB | 2025 GB | 8K / 8K |