Q4_K_M · 4K context
Gemma 4 12B 11.95B dense model · estimated Q4_K_M memory about 8GB
A single 11.95B parameter dense model supports 256K (262,144) native contexts. High-speed standalone operation is possible in 16GB~24GB GPU and Mac environments.
- Estimated Q4_K_M memory
- about 8GB
- total parameters
- 11.95B
- active parameter
- 11.95B
- native context
- 256K
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 55· 5 shown
Comfortable fit · Q4_K_M · Headroom 7.0GB
₩2,239,360
47.6 ~ 52.7 tok/s
Comfortable fit · Q4_K_M · Headroom 12.0GB
₩2,650,000
27.8 ~ 30.9 tok/s
Comfortable fit · Q4_K_M · Headroom 12.0GB
₩2,990,000
31.3 ~ 34.8 tok/s
Comfortable fit · Q4_K_M · Headroom 7.0GB
₩3,022,355
91.4 ~ 104.1 tok/s
Comfortable fit · Q4_K_M · Headroom 33.0GB
₩3,035,000
27.8 ~ 30.9 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.
Gemma 4 12B Local Serving Run Recipe
Selecting a device changes the quantization, safety context, GPU offload, Flash Attention, KV cache, and batch start values.
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.