On a 8 GB Mac, 12 catalog models run fully on the GPU at an 8,192-token context. The most capable is gemma-4-12B-it at Q4_K_M (needs ~7.8 GiB). Pick a smaller model or a lower quant for more headroom.
Figures assume a 8 GB unified-memory Mac (one pool shared by CPU and GPU), judged at an 8,192-token context. Speeds depend on the specific chip — see the GPU pages.
gemma-4-12B-it at Q4_K_M · 12B params · needs ~7.8 GiB
One command to run it (llama.cpp):
llama-server -m gemma-4-12b-it-Q4_K_M.gguf -c 8192 -ngl 999| Model | Sweet-spot quant | Fits in |
|---|---|---|
| gemma-4-12B-it google | Q4_K_M Runs fully on GPU | ~7.8 GiB |
| Qwen3-8B Qwen | Q4_K_M Runs fully on GPU | ~6.8 GiB |
| DeepSeek-R1-Distill-Llama-8B deepseek-ai | Q4_K_M Runs fully on GPU | ~6.6 GiB |
| gemma-4-E4B-it google | QAT-Q4_0 Runs fully on GPU | ~5.8 GiB |
| DeepSeek-R1-Distill-Qwen-7B deepseek-ai | Q4_K_M Runs fully on GPU | ~5.7 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 |
| Qwen3-Embedding-4B Qwen | Q4_K_M Runs fully on GPU | ~4.2 GiB |
| Phi-4-mini-instruct microsoft | Q8_0 Runs fully on GPU | ~5.7 GiB |
| SmolLM3-3B HuggingFaceTB | BF16 Runs fully on GPU | ~7.4 GiB |
| dots.ocr rednote-hilab | BF16 Runs fully on GPU | ~7 GiB |
| Qwen3-ASR-1.7B Qwen | Q8_0 Runs fully on GPU | ~2.7 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