Qwen3.8-Escha-W2

About

What Qwen3.8-Escha-W2 is

Qwen3.8-27B-Escha-W2 — 2-bit quantized (escha) By Escha Labs Inc. Escha-W2 is a 2-bit quantized build of Qwen3.8-27B. It holds the full 27B parameter count in 10.15 GB of weights — small enough that the whole model, its KV cache and a 64k context fit on a single 24 GB consumer card, with room left over (or 128k context on the same card with a tuned config — see Long context). On the three axes we measured it against a same-backend FP8 reference, this build is not measurably worse: it is ahead on commonsense reasoning, behind by exactly one question on GPQA-Diamond, and ahead on LiveCodeBench within that benchmark's own noise. Contents This repo holds only the model. The runtime that serves it lives in EschaLabs/escha-runtime-qwen3dense — an SGLang build with the decode kernels this format needs. That is the engine this model is served and measured on throughout this card. Quickstart Sanity check before serving — all three must print True: (import sglang is part of the check on purpose — an earlier torch, escha-only version passed on a box that could not actually serve.) Then, from another shell: If generation is fluent but wrong — confident, well-formed nonsense — you are almost certainly on transformers < 5.8, which loads this architecture with a silently different attention path. Upgrade before reporting a quality bug. Connecting a client opencode.json in this repo is a working provider block — drop it in and it points at the local server. The launch script binds to localhost. If you set HOST=0.0.0.0 to reach it from another machine, set APIKEY at the same time; the server has no auth of its own. Thinking mode This is a thinking model. Toggle it through chattemplatekwargs — a top-level enablethinking is ignored: When thinking is on, the answer may arrive split across both reasoningcontent and content — read both, or you will score empty strings. THINK=0 on the launch script defaults it off. reasoningeffort — the knob most people should touch first The default is xhigh, and it is the single biggest lever on how long an answer takes. It goes in chattemplatekwargs alongside enablethinking, and it only applies while thinking is on. Two things to know before you re

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys qwen3-8-escha-w2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen3-8-escha-w2 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3-8-escha-w2","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More language models