Dedicated GPU memory guides
These Windows/NVIDIA guide pages use dedicated GPU memory as the primary fit budget and keep partial offload separate from a full GPU fit.
Google · Gemma
Gemma 3 12B local AI fit guide
Review available GGUF variants, quantization choices, and conservative memory-planning levels for running Gemma 3 12Blocally.
- Parameters
- 12B
- Size class
- medium
- Use cases
- chat, reasoning, rag
- Catalog context
- 128,000 tokens
GGUF variants
| Variant | Quantization | Estimated file | Minimum load | Planning memory |
|---|---|---|---|---|
| Gemma 3 12B · Q4_K_M | Q4_K_M | 7.3 GB | 8.4 GB | 9.9 GB |
| Gemma 3 12B · Q5_K_M | Q5_K_M | 8.6 GB | 9.9 GB | 11.6 GB |
GPU compatibility
GPUs with a verified memory-fit path for Gemma 3 12B
These pages compare this model's recorded GGUF variants against the dedicated VRAM of selected NVIDIA GPUs. They are deterministic memory-fit checks, not performance benchmarks.
Apple Silicon unified-memory guides
Apple Silicon pages use conservative unified-memory budgets and Metal-capable local inference terminology instead of treating the Mac as a CUDA workstation.
Fit caveats
These are deterministic memory-planning checks, not benchmark claims. Context length, runtime settings, offload behavior, and concurrent apps can change practical fit.