On a 12 GB GPU, 12 catalog models run fully on the GPU at an 8,192-token context. The most capable is Kimi-VL-A3B-Instruct at IQ4_XS (needs ~11.2 GiB). Pick a smaller model or a lower quant for more headroom.
Figures assume a 12 GB GPU paired with 32 GB of system RAM (a typical desktop), judged at an 8,192-token context. Speed depends on the specific card — this page ranks by fit, not speed.
Kimi-VL-A3B-Instruct at IQ4_XS · 16.4B params · needs ~11.2 GiB
One command to run it (llama.cpp):
llama-server -m Kimi-VL-A3B-Instruct.i1-IQ4_XS.gguf -c 8192 -ngl 999| Model | Sweet-spot quant | Fits in |
|---|---|---|
| Kimi-VL-A3B-Instruct moonshotai | IQ4_XS Runs fully on GPU | ~11.2 GiB |
| DeepSeek-R1-Distill-Qwen-14B deepseek-ai | Q4_K_M Runs fully on GPU | ~11.2 GiB |
| Qwen3-14B Qwen | Q4_K_M Runs fully on GPU | ~11 GiB |
| Phi-4-reasoning microsoft | Q4_K_M Runs fully on GPU | ~11.4 GiB |
| phi-4 microsoft | Q4_K_M Runs fully on GPU | ~11.2 GiB |
| gemma-4-12B-it google | Q4_K_M Runs fully on GPU | ~7.8 GiB |
| Qwen3-8B Qwen | Q8_0 Runs fully on GPU | ~10.6 GiB |
| DeepSeek-R1-Distill-Llama-8B deepseek-ai | Q8_0 Runs fully on GPU | ~10.3 GiB |
| gemma-4-E4B-it google | Q8_0 Runs fully on GPU | ~8.9 GiB |
| DeepSeek-R1-Distill-Qwen-7B deepseek-ai | Q8_0 Runs fully on GPU | ~9.3 GiB |
| Qwen3-Embedding-8B Qwen | Q4_K_M Runs fully on GPU | ~6.4 GiB |
| gemma-4-E2B-it google | Q8_0 Runs fully on GPU | ~5.7 GiB |
Derived live from the fit engine + catalog at an 8,192-token context. "Fits in" is the modelled VRAM the sweet-spot quant needs (weights + KV cache + overhead). Speed depends on your specific card — check a GPU page or the calculator.
selected to compare · pick at least 2