cd /news/artificial-intelligence/city96-s-quantized-umt5-xxl-shrinks-… · home › topics › artificial-intelligence › article
[ARTICLE · art-172868] src=alphasignal.ai ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

City96's Quantized UMT5-XXL Shrinks Wan Video Pipelines by 7GB

City96's GGUF-quantized build of Google's UMT5-XXL text encoder has become the default encoder for local Wan 2.1/2.2 video pipelines, shrinking the 6-billion-parameter model from 22.7 GB in F32 to as little as 2.86 GB (Q3_K_S), with a Q4 file at about 3.5 GB. The Hugging Face repository reported more than 819,000 downloads in the cited month, and the build works with ComfyUI-GGUF, llama.cpp, Ollama, LM Studio and Docker Model Runner. City96 recommends Q5_K_M (4.15 GB) or larger because llama.cpp cannot build imatrix calibration for T5.

key takeaway

Swap the 22.7 GB F32 UMT5-XXL encoder for City96's Q5_K_M GGUF (4.15 GB) or larger in Wan video pipelines, since llama.cpp cannot build imatrix calibration for T5 and smaller quants lack that calibration.

read2 min views3 publishedNov 19, 2026
City96's Quantized UMT5-XXL Shrinks Wan Video Pipelines by 7GB
Image: Alphasignal (auto-discovered)

A GGUF-quantized build of Google's UMT5-XXL encoder is quietly powering most local Wan video pipelines, shrinking a 22GB model to under 4GB.

  • GGUF-quantized build of Google's UMT5-XXL encoder , 6B params, Apache 2.0
  • Over 819,000 downloads last month, now the default text encoder for Wan video workflows
  • Quants range from 2.86 GB (Q3_K_S) to 11.4 GB (F16), down from 22.7 GB in F32
  • Q5_K_M or larger recommended because llama.cpp cannot build imatrix calibration for T5
  • Works with ComfyUI-GGUF , llama.cpp, Ollama, LM Studio and Docker Model Runner
  • Primary use case: Wan 2.1/2.2 text-to-video pipelines where VRAM budget is tight

City96’s GGUF conversion of Google’s UMT5-XXL encoder has become a common component in ComfyUI video workflows. The repository reported more than 819,000 downloads during the cited month. Hugging Face download counts represent file requests and can include repeat downloads, but the volume shows broad adoption across the open video stack.

City96 repackaged the roughly six-billion-parameter encoder in quantized GGUF files that require far less memory than the original weights. A Q4 file occupies about 3.5 GB, leaving substantially more room for a 14B-class Wan diffusion transformer, VAE, runtime buffers, and optional image or audio components.

One encoder, ten memory budgets #

The source checkpoint, google/umt5-xxl, is a multilingual T5 model. Video pipelines use its encoder to transform prompt tokens into conditioning vectors, so this repository omits the decoder and packages the required weights in GGUF, a format designed for efficient and quantized tensors.

Published GGUF files and approximate sizes
Quantization Size Practical use
--- --- ---
Q3_K_S 2.86 GB Severe memory constraints
Q3_K_M 3.06 GB Severe memory constraints
Q4_K_S 3.50 GB Low-VRAM workflows
Q4_K_M 3.66 GB Low-VRAM workflows
Q5_K_S 4.05 GB Balanced default
Q5_K_M 4.15 GB Publisher-recommended minimum
Q6_K 4.67 GB Higher precision
Q8_0 6.04 GB Near-full precision
F16 11.4 GB Unquantized half precision
F32 22.7 GB Full precision

Compared with the 11.4 GB F16 file,

This story is for Pro members #

You've reached the end of the free preview. Upgrade to AlphaSignal Pro to read the full article - and everything else behind the paywall.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @city96 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/city96-s-quantized-u…] indexed:0 read:2min 2026-11-19 · —