16GB Encoder8.41 GB8GB+ VRAMgguf🔒 Gated — HF login required

gemma4-12b-with-proj-ltx-2.5-Q4_K_M.gguf

Gemma 4 12B with Projection GGUF Q4_K_M (Community)

Community Q4_K_M GGUF quantization of the Gemma 4 text encoder — 8.41GB, 1.1GB smaller than Q5_K_M. That headroom is what lets a 16GB card pair the encoder with a Q4_K_M or Q5_K_M transformer instead of being forced down to Q3_K_S. Projection layer is bundled, so no separate text-projection file. The repo inherits LTX 2.5's gating — sign in and accept the license. Requires the ComfyUI-GGUF custom node. Place in models/text_encoders/.

Released 2026-09-06 · Source: elix3r/gemma4-12b-with-proj-ltx-2.5-GGUF (HuggingFace)Added alongside Q2_K in the September update to the repo; Q5_K_M was the only quant available before.

Download gemma4-12b-with-proj-ltx-2.5-Q4_K_M.gguf

Official HuggingFace repo — sign in and click "Agree and Access" to accept the LTX 2.5 license before this downloads. 8.41 GB · Free.

Install path: ComfyUI/models/text_encoders/ + gemma4-12b-with-proj-ltx-2.5-Q4_K_M.gguf

No 8GB GPU? Try gemma4-12b-with-proj-ltx-2.5-Q4_K_M.gguf online — free generation included

Skip the 8.41 GB download and ComfyUI setup. Generate a 6-second video using this exact model in your browser, ~30 seconds.

Try this model online — free →

When to choose gemma4-12b-with-proj-ltx-2.5-Q4_K_M.gguf

Pick Q4_K_M over Q5_K_M when the 1.1GB saved lets you step up a transformer quant on 16GB. Q4_K_M is the usual sweet spot for LLM-class GGUF quants; the prompt-understanding hit versus Q5_K_M is small relative to the transformer quality gain.

Will this run on my GPU?

Minimum: 8GB VRAM.

GPUVRAMVerdict
RTX 3060 12GB12GBComfortable
RTX 4060 Ti / 4070 (16GB)16GBComfortable
RTX 4070 Ti SUPER / 4080 (16GB)16GBComfortable
RTX 3090 (24GB)24GBComfortable
RTX 4090 (24GB)24GBComfortable
RTX 5090 / A6000 (32GB+)32GBComfortable

How to use gemma4-12b-with-proj-ltx-2.5-Q4_K_M.gguf

  1. Download the file from HuggingFace.
  2. Place it in ComfyUI/models/text_encoders/ inside your ComfyUI directory.
  3. Restart ComfyUI (or refresh the model list from the menu).
  4. Load a compatible workflow — see below.

See the LTX 2.5 ComfyUI setup guide for the full file list and install order.

Don't want to run this locally? Try gemma4-12b-with-proj-ltx-2.5-Q4_K_M.gguf online with a free generation — no GPU, no install, ~30 seconds per clip.

Common issues

ComfyUI doesn't see the file after I downloaded it

Make sure the file is in ComfyUI/models/text_encoders/ (not a subfolder). Restart ComfyUI fully — the menu refresh sometimes misses new files. Filename must match exactly: gemma4-12b-with-proj-ltx-2.5-Q4_K_M.gguf.

CUDA out of memory error when loading the model

gemma4-12b-with-proj-ltx-2.5-Q4_K_M.gguf needs ~8GB VRAM minimum. If you're hitting OOM: • Enable Sequential Offloading in ComfyUI settings • Lower the resolution (768×512 instead of 1280×704) — both dimensions must be divisible by 32 • Reduce frame count (65 frames instead of 161) — must be 8n+1 • Use a smaller variant — see Related models below.

Free newsletter

Get notified when Gemma 4 12B with Projection GGUF Q4_K_M (Community) updates

Occasional updates on what's new in LTX 2.5 — new quants, LoRAs, releases — with our hands-on verdict on whether they're worth re-downloading. No fixed cadence.

No spam. Sent occasionally when there's real news. Unsubscribe in one click.

Related models