landscape
Search⌘KSubmit a productSign in

Map / Infrastructure / Inference & Compute / Escha Labs

Escha Labs

2-bit compressed LLMs that run 27B to 35B models on one consumer GPU

CuratedInference OptimizationLinux

I use this adds Escha Labs to your stack and finds people with similar stacks. Every mark feeds the counts on Pulse. Sign in to mark it.

No ratings yet

Who uses it

0 use this
0use it now
0tried it, dropped it
0want to try

Nobody has marked it yet. Press I use this, Tried it or Want to try to be the first.

Ratings

Only from people who use it or tried it
No ratings yet

The first rating comes from someone who uses Escha Labs or tried it.

Use Escha Labs?

Sign in, mark it as I use this or Tried it, then rate it.

Sign in to rate

What it does

Escha Labs builds extreme low-bit compression for large language models. Its first releases are 2-bit builds of Qwen3.6-35B-A3B and Qwen3.8-27B: the 35B model shrinks from 71.9 GB to 12.3 GB and runs on a single 24 GB NVIDIA card, with quality the company reports as close to its FP8 baseline. The weights and its serving runtimes are Apache-2.0 on Hugging Face; for now they run on Linux with NVIDIA GPUs only.

Alternatives on the map

All 58 alternatives

Inference & Compute, starting with the other Inference Optimization.

Compare with

People who use it also use

Not enough marks yet to tell. When people who use Escha Labs mark the rest of their stack, it shows up here.

Open website