gemma-4-12B-coder-fable5-composer2.5-v1

Llama family · 12.0B params

Evidence: 0 sourced runs · 1 awaiting review · 1 independent source · first recorded Aug 17, 2026. What these labels mean.

What the gemma-4-12B-coder-fable5-composer2.5-v1 numbers mean

The fastest result on our board is 85.3 output tok/s on an RTX 5090 at Q8_0 with a 2048-token context. That is about 11.7 ms per generated token — 500 tokens takes roughly 5.9 seconds. Prompt processing on the same record runs at 330.7 tok/s, so a 2,000-token prompt is read in about 6.0 seconds.

How much VRAM does gemma-4-12B-coder-fable5-composer2.5-v1 need?

gemma-4-12B-coder-fable5-composer2.5-v1 has 12.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Models with a similar footprint

Ranked by distance from gemma-4-12B-coder-fable5-composer2.5-v1's parameter count. Full benchmark board.

All benchmarks Methodology