🔧 Patched chat template
chat_template.jinja differs from Google's Gemma 4 Canonical Chat Template
(2026-07-09) by one intentional change; everything else is untouched.
The canonical template suppresses the thinking channel at the start of a normal model
turn, but emits nothing after a tool response when enable_thinking is false. The model
may then open a thinking channel on its own, and a quantized model sometimes writes the
literal word thought into the answer. This patch gives the tool_response branch the
same suppression:
{%- elif ns.prev_message_type == 'tool_response' -%}
{%- if enable_thinking -%}
{{- '<|channel>thought\n' -}}
{%- else -%}
{{- '<|channel>thought\n<channel|>' -}}
{%- endif -%}
{%- endif -%}
Only that case changes — the other prompt paths render byte-identical to the canonical
template. To get stock behaviour, replace chat_template.jinja with the one from the
base model repo; the weights are unaffected.
- Downloads last month
- 172
Model size
2B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ToPo-ToPo/gemma-4-12B-it-qat-mlx-4bit
Base model
google/gemma-4-12B Finetuned
google/gemma-4-12B-it