Everything here is free and stays free — the format spec, the nodes, the workflows, the cartridges, the LoRAs. If it saved you a night of debugging (it contains several hundred of mine), tips keep the 5090 warm:

• ☕ Buy me a coffee on Ko-fi

• 💛 Sponsor on GitHub

• 🔁 Liberapay (recurring)

• ⚡ Or right here: the Civitai tip button on this page sends Buzz directly.

A one-hop Q8_0 quantization of the TRUE base google/gemma-3-12b-it, in the loader format the JoyAI-Echo ComfyUI node pack expects. This is the exact text encoder the LTX-2.3 / JoyAI-Echo DiT family was trained against — nothing finetuned, nothing re-quantized.

Files

• gemma3-12b-BASE-clean-Q8_0.gguf — 12.45 GiB, reference tier, ~0.55% RMS error vs bf16. Start here.

• gemma3-12b-BASE-clean-Q4_0.gguf — 7.31 GiB, half-size tier, embedding table held at Q8_0. Take this if those 5 GiB are what fit your card.

Both are one-hop quantizations of the same clean bf16 base, in the same loader format.

Why this exists

The commonly circulated gemma3-12b-joyecho-Q8_0.gguf is not base Gemma. Its architecture string is a different, modified model, and it was built from an fp8 checkpoint and then re-quantized — double quantization; it still carries .comfy_quant marker tensors from the fp8 stage. In my renders it produced duplicated subjects and identity corruption.

The DiT reads base Gemma's embedding space. Any encoder drift degrades output structurally, not subtly — so this is one of the few places in the stack where the wrong file does not merely cost quality, it changes what you get.

Symptoms of the wrong encoder

• Two of the same person in one frame, or a subject that splits
  Why: embedding drift from a modified or double-quantized encoder.
  Fix: use one of these files.

• Prompt adherence stays vague no matter how you word it
  Why: the DiT is reading a slightly different embedding space than it was trained on.
  Fix: same — the encoder sits upstream of everything, so it is worth ruling out before you tune anything downstream.

Everything else I've published

• All models on Hugging Face

• JoyAI-Echo multishot patch — nodes, releases, issues

• LTX-2.3 Multishot Lite — the core-node workflow