ratelimit now
Get updates

Qwen 3.8 27B

By Alibaba. 4 results on 4 boards, copied as published. Different boards, different metrics: don't add them up.

License (as listed)Apache 2.0
Hosting regionNot confirmed
Boards4
Code
  • 86%Vals AI — SWE-bench Verified

    Qwen 3.8 27B · % resolved · board #15

    Mini-SWE-agent · as of 2026-09-01 Stale ↗

  • 84%Vals AI — LiveCodeBench

    Qwen 3.8 27B · Accuracy % · board #43

    Vals AI implementation (no agent) · as of 2026-09-01 Stale ↗

Agentic / terminal

No result on the boards we captured

Websites
  • 1591LMArena WebDev Arena

    qwen3.8-27b · Arena score · board #32

    LMArena WebDev (agentic front-end tasks) · as of 2026-10-22 ↗

  • 64.85%Vals AI Vibe Code Bench v1.1

    Qwen 3.8 27B · Score % · board #49

    OpenHands · as of 2026-10-20 ↗

Design

No result on the boards we captured

Android

No result on the boards we captured

iOS

No mature public leaderboard

Available in

No plan row in our pricing data names this model version.

Use cases with this model

Gemma 4 E4BLlama 3.2 3BQwen 3.8 27BPromo account

Llama: only local infra (e.g., Llama 3.2 3B at 124 tok/s on a jailbroken PS5)

Builder
@Techjunkie_Aman
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

Qwen 3.8 27B

SwarmLLM — splits Qwen 3.8 27B across nearby devices in browser tabs

Builder
@itsharmanjot
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

ZedQwen 3.8 27B

2-bit quantized Qwen 3.8 27B drafter, "Zero speed penalty (76 t/s)"

Builder
@analogalok
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

Qwen 3.8 27B

"running Qwen 3.8 27B on my own personal computer. I built a AAA-level website in less than a day with $0 in API consumption"

Builder
@DanielMuvdiYT
Posted
Plan
—
Cost
In tool range
WebsitesRead the post

x.com · link re-checked 2026-10-16

Same family: Qwen 7

Mistral Large 4Model test

"qwen 3.8 flash next … built the whole thing on my dgx spark in 2.5 hours", where Mistral Large 4 "burned 233k tokens and never wrote a single file"

Builder
@sudoingX
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

Qwen family

Data-analyst agent: "Qwen handles the main agent work", Vercel runs the loop

Builder
@Sumanth_077
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

Kimi K3GLM-5.3Qwen 3.8 Max+2Model test

Test: "Qwen 3.8 Max (max): 25.7 - DeepSeek V4.1 Flash (max): 21.7 - Kimi K3 (default): 23 - GLM-5.3 (max): 19 - Mistral Large 4 (high, its max): 15"

Builder
@PawelHuryn
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

Kimi K3GLM 5.3Qwen3.8 Max 0902+1Vendor post

Self-playing Flappy Bird and Missile Command games, each one-shot in a single HTML file, comparing 4 open models

Builder
EmpirioLabs AI
Posted
Plan
Run on the EmpirioLabs platform
Cost
Not disclosed
WebsitesDesignRead the post

empiriolabs.ai · web source · link re-checked 2026-10-16

Qwen family

So long Quickbooks! Thanks to local Qwen 3.8 27b (with some code review by Claude) I have built my own accounting system … $460 annual savings.

Builder
@lonseidman
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

Qwen family

A 5.9GB ternary compression of Qwen 3.8 27B building a frontend in one shot on an RTX 3060 12GB ("1 hour 24 minutes")

Builder
@sudoingX
Posted
Plan
—
Cost
Not disclosed
DesignRead the post

x.com · link re-checked 2026-10-16

All 7 Qwen use cases →

Sources

lmarena.ai/leaderboard/webdev vals.ai/benchmarks/vibe-code vals.ai/benchmarks/swebench vals.ai/benchmarks/lcb

The weekly diff

What changed in AI coding plans: prices, limits, resets. Email signups open soon. Until then, updates go out on X.

Follow @QuietlyByG on X RSS feed

No email form yet, so we don't collect any email addresses.