Q4_K_M · 4K context
K2 Horizon 0.9B 0.9B dense model · estimated Q4_K_M memory about 2GB
This is the smallest compact model in the K2 Horizon family. It is a first candidate for lightweight classification/summarization/local automation, and a distinction must be made between long context limits and the context length to be maintained on actual devices.
- Estimated Q4_K_M memory
- About 2GB
- total parameters
- 0.9B
- active parameter
- 0.9B
- native context
- 128K
Start with a model
Find hardware for this model
Also running document search?
Reserve this for embedding and reranking models sharing the same GPU or unified memory. Leave it at none if they run separately on the CPU.
Matching devices 44· 5 shown
Comfortable fit · Q4_K_M · Headroom 12.0GB
₩1,180,000
154 ~ 172.1 tok/s
Comfortable fit · Q4_K_M · Headroom 12.0GB
₩1,525,000
149.4 ~ 167.5 tok/s
Comfortable fit · Q4_K_M · Headroom 12.0GB
₩1,669,000
202.1 ~ 225.2 tok/s
Comfortable fit · Q4_K_M · Headroom 19.0GB
₩1,925,000
154 ~ 172.1 tok/s
Comfortable fit · Q4_K_M · Headroom 19.0GB
₩1,950,000
149.4 ~ 167.5 tok/s
Price is the range midpoint, with a basic host added for GPU-only prices. Speed is an estimate for the same model and 4K input.
If you want to choose equipment again
You can first narrow down the model configurations based on budget, noise level, operating system and whether it's acceptable used.