Gemma4-12B Cross-Platform Residency and Benchmarking
Parent: Local Model Performance Evaluation: Ollama, MLX, and Hardware Architectures · Published reference · snapshot 2026-09-30
↓ Facts as markdownall context files
Source-anchored research for Gemma4-12B Cross-Platform Residency and Benchmarking. Run status: COMPLETED.
These notes link each claim to its source. Some citations identify archived research reports that are no longer hosted on this site. A published reference means the content is available; it does not certify independent review or accuracy.Read the editorial policy and follow the sources before relying on a claim.
Measurements and reference values
- Gemma4-12B quantized at 4-bit occupies ~7.8 GB VRAM, leaving 8.2 GB headroom in a 16GB VRAM pool for up to 32k token KV cache and activation workspaces. (high confidence) [source]
- When running completely resident in RTX 5080 GDDR7 VRAM (~1000 GB/s), Gemma4-12B generates ~85-92 tokens per second, roughly double the ~42-45 tokens per second achieved on Apple Silicon M5 Max (~400 GB/s). (high confidence) [source]
Comparisons and alternatives
- Serving Gemma4-12B via Ollama Metal introduces a 10-15% throughput penalty compared to native MLX-LM due to runtime translation and generic Metal kernel dispatch in ggml. (high confidence) [source]
Facts and statements
- Pre-allocation of static tensor workspaces in Tinygrad or TensorRT avoids CUDA and Metal memory fragmentation during extended generation passes. (high confidence) [source]
Children
- No children recorded.