On a 32 GB GPU, 12 catalog models run fully on the GPU at an 8,192-token context. The most capable is Kimi-Linear-48B-A3B-Instruct at IQ4_XS (needs ~29.6 GiB). Pick a smaller model or a lower quant for more headroom.
Figures assume a 32 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-Linear-48B-A3B-Instruct at IQ4_XS · 49.1B params · needs ~29.6 GiB
One command to run it (llama.cpp):
llama-server -m moonshotai_Kimi-Linear-48B-A3B-Instruct-IQ4_XS.gguf -c 8192 -ngl 999| Model | Sweet-spot quant | Fits in |
|---|---|---|
| Kimi-Linear-48B-A3B-Instruct moonshotai | IQ4_XS Runs fully on GPU | ~29.6 GiB |
| Qwen3.6-35B-A3B Qwen | Q4_K_M Runs fully on GPU | ~23.9 GiB |
| Qwen3-Omni-30B-A3B-Instruct Qwen | Q4_K_M Runs fully on GPU | ~19.6 GiB |
| Qwen2.5-VL-32B-Instruct Qwen | Q4_K_M Runs fully on GPU | ~22.9 GiB |
| DeepSeek-R1-Distill-Qwen-32B deepseek-ai | Q4_K_M Runs fully on GPU | ~22.9 GiB |
| Qwen3-32B Qwen | Q4_K_M Runs fully on GPU | ~22.8 GiB |
| gemma-4-31B-it google | Q4_K_M Runs fully on GPU | ~19.3 GiB |
| GLM-4.7-Flash zai-org | Q6_K Runs fully on GPU | ~28.8 GiB |
| Qwen3-Coder-30B-A3B-Instruct Qwen | Q4_K_M Runs fully on GPU | ~20.3 GiB |
| Qwen3-30B-A3B-Instruct-2507 Qwen | Q4_K_M Runs fully on GPU | ~20.3 GiB |
| Qwen3.6-27B Qwen | Q8_0 Runs fully on GPU | ~31.9 GiB |
| gemma-4-26B-A4B-it google | Q8_0 Runs fully on GPU | ~30 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