MLX bf16 conversion of google/gemma-4-31b-it for Apple Silicon (mlx-vlm).
google/gemma-4-31b-it (license: gemma)mlx-vlm 0.6.3 — mlx_vlm.convert --hf-path google/gemma-4-31b-it --mlx-path . --dtype bfloat16from mlx_vlm import load, generate
model, processor = load("ToPo-ToPo/gemma-4-31b-it-mlx-bf16")
This is a derivative of Google Gemma. Use is governed by the Gemma Terms of Use and the Gemma Prohibited Use Policy. Weights were converted/quantized to MLX format (modification notice per the Gemma Terms).
Use google/gemma-4-31b-it-assistant — Google's official MTP drafter for
this model. It loads directly in mlx-vlm (>= 0.6.3), needs no conversion, and speculative
decoding is lossless. Drafters are size-specific and not interchangeable across Gemma 4
variants.
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.
model-00002-of-00012.safetensors 5.4 GBmodel-00004-of-00012.safetensors 5.4 GBmodel-00009-of-00012.safetensors 5.4 GBmodel-00005-of-00012.safetensors 5.3 GBmodel-00010-of-00012.safetensors 5.3 GBmodel-00007-of-00012.safetensors 5.3 GBmodel-00001-of-00012.safetensors 5.2 GBmodel-00011-of-00012.safetensors 5.2 GBmodel-00006-of-00012.safetensors 5.2 GBmodel-00008-of-00012.safetensors 5.2 GBmodel-00003-of-00012.safetensors 5.2 GBmodel-00012-of-00012.safetensors 4.6 GBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo ToPo-ToPo/gemma-4-31b-it-mlx-bf16 ./model-folder