Gemma 4 12B Coder — abliterated (GGUF, deprecated) ⚠️ Deprecated — do not use for new work. superseded by SFT v5 + abliterated (GGUF) — keeps SFT v5's tool calling (gate SHIM 8/8) plus the same uncensoring. Use that for new work. Replaced by tpls/gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated GGUF . Uncensored gemma 4 12B coder for local, agentic tool use — GGUF quantizations for llama.cpp / Ollama. Run it: llama server hf tpls/gemma 4 12B coder fable5 composer2.5 v1 abliterated GGUF:Q4 K M jinja (full commands below). ⚠️ Tool calling needs the recovery shim. The model emits gemma 4's native tool markup, which llama.cpp jinja under parses — wrap your endpoint with the tool shim (see Tool calling below) to get standard tool calls . At a glance Type GGUF quantizations · llama.cpp / Ollama Techniques abliteration → imatrix quant → tool shim Tool calling native markup — recover via the tool shim (below); not yet gate measured Status ⚠️ Deprecated → tpls/gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated GGUF Use llama server hf tpls/gemma 4 12B coder fable5 composer2.5 v1 abliterated GGUF:Q4 K M jinja Use it Files Sizes and a one click loader are in the file browser…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy