Google
Gemma 4 12B Coder Fable5 Composer2.5 V1
Gemma 4 12B Coder Fable5 Composer2.5 V1 is an open-weights model by Google. It is listed as in-progress on the local.ai leaderboard.
open weights
Parameters
undisclosed
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2026-06-30
Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.
Does it fit your hardware?
Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.
Params not disclosed — no size estimate.Actual files on HuggingFace
| File | Size |
|---|---|
| model.safetensors | 22.28 GB |
GGUF: yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF · 376,960 downloads
GGUF: llmfan46/gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-GGUF · 12,563 downloads
| File | Size | |
|---|---|---|
| gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-F16.gguf | 22.20 GB | download |
| gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-Q4_K_M.gguf | 6.87 GB | download |
| gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-Q4_K_S.gguf | 6.54 GB | download |
| gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-Q5_K_M.gguf | 7.96 GB | download |
| gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-Q5_K_S.gguf | 7.77 GB | download |
| gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-Q6_K.gguf | 9.11 GB | download |
| gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-Q8_0.gguf | 11.80 GB | download |
| gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-mmproj-F16.gguf | 0.11 GB | download |
What you save self-hosting this model
Uses the model's own API price when it exists; otherwise the closest commercial equivalent.
Waiting for hardware detection…
RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.