Q4_K_M
500 GBMin VRAM: 575 GB
Recommended VRAM: 650 GB
Min RAM: 750 GB
Context: 8K / 8K
Loading model details...
Fetching variants, compatibility details, and metadata.
Loading model details...
Fetching variants, compatibility details, and metadata.
Share Kimi K2.5 with someone who is deciding what to run locally.
Social proof
0% of 996 scanned PCs run Kimi K2.5 fully on GPU.
200 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
500 GBMin VRAM: 575 GB
Recommended VRAM: 650 GB
Min RAM: 750 GB
Context: 8K / 8K
Q5_K_M
625 GBMin VRAM: 718.8 GB
Recommended VRAM: 812.5 GB
Min RAM: 938 GB
Context: 8K / 8K
Q8_0
1000 GBMin VRAM: 1150 GB
Recommended VRAM: 1300 GB
Min RAM: 1500 GB
Context: 8K / 8K
FP16
2000 GBMin VRAM: 2300 GB
Recommended VRAM: 2600 GB
Min RAM: 3000 GB
Context: 8K / 8K
| Quantization | File Size | Min VRAM | Recommended VRAM | Min RAM | Context |
|---|---|---|---|---|---|
| Q4_K_M | 500 GB | 575 GB | 650 GB | 750 GB | 8K / 8K |
| Q5_K_M | 625 GB | 718.8 GB | 812.5 GB | 938 GB | 8K / 8K |
| Q8_0 | 1000 GB | 1150 GB | 1300 GB | 1500 GB | 8K / 8K |
| FP16 | 2000 GB | 2300 GB | 2600 GB | 3000 GB | 8K / 8K |