Notes from the work

One email when a tutorial or migration write-up goes live. Nothing else, and an unsubscribe link in every email.

LeanZero

Two people in Romania doing Atlassian migrations, Forge apps and practical AI work for teams that would rather talk to the person doing the job. Most of what we learn ends up on this site.

Services

  • Atlassian migrations
  • Atlassian FastShift
  • Atlassian maintenance
  • Forge app development
  • AI development consultation

Topics

  • Jira
  • Jira Service Management
  • Confluence
  • Bitbucket
  • Atlassian Forge
  • Cloud Migration
  • Local AI
  • AI Coding
  • Certifications
  • Atlassian Team
  • All topics

Company

  • Blog
  • Tutorials
  • Contact

Community

  • Join Discord
  • Support this site

© 2026 LeanZero. All rights reserved.

Privacy policyTerms of service24/7 SupportTrust centerSecurityDPALegal notice
  1. Home
  2. Blog
Knowledge Base

Atlassian insights & tutorials

Real Atlassian solutions to real problems — no fluff, no SEO spam.

Read the latestFollow the tutorials
JiraConfiguration, workflows and fixes from real projectsLocal AIModels and agents running on your hardwareAI codingCoding tools and workflows tested in practice

Articles 11

All topicsAI CodingAtlassian ForgeAtlassian TeamBitbucketCertificationsCloud MigrationCogniRunnerConfluenceCost SlasherJiraJira Service ManagementLeanZero ManagementLocal AISentinel Vault
MXFP8 vs Q8: 10x the weight error, 1% the perplexity
ArticleAI CodingLocal AI

MXFP8 vs Q8: 10x the weight error, 1% the perplexity

I quantised real Qwen3-Coder weights both ways on an M3 Ultra. MXFP8 reconstructs them about 10x worse than 8-bit affine at identical size — and then costs only 1% perplexity end to end. Both numbers are true, and the gap between them is the interesting part.

Mihai PerdumAug 1, 202614 min read

More articles

MLX vs GGUF on Apple Silicon: Benchmarking the Same Local Model Two Ways
ArticleAI CodingLocal AI

MLX vs GGUF on Apple Silicon: Benchmarking the Same Local Model Two Ways

We built a harness that makes local coding agents produce real software, grades it by running it, and ran the same model as GGUF and MLX. Here's the harness, its modes and archetypes — and which build to run.

Mihai PerdumJul 2, 202612 min read
Previous
Page2of 2
Next

Found my advice helpful?

If I helped you solve something for free, coffee money is always appreciated (but never expected).

Buy Me a Coffee

Join the community

Join the community to ask questions, share your work, and connect with other professionals.

Join Discord

Recent writings

View all
Qwen3.8-Flash-Next on a Mac Studio vs OpenRouter: what it took to reach 0.6932
ArticleLocal AI

Qwen3.8-Flash-Next on a Mac Studio vs OpenRouter: what it took to reach 0.6932

Mihai Perdum20 min read
Four Qwen3.8-27B fine-tunes and merges on a coding benchmark: none beat the base
ArticleAI Coding

Four Qwen3.8-27B fine-tunes and merges on a coding benchmark: none beat the base

Mihai Perdum17 min read
Best local image generation model on a Mac? ERNIE-Image Turbo won our blind test
ArticleAI Coding

Best local image generation model on a Mac? ERNIE-Image Turbo won our blind test

Mihai Perdum19 min read
v0.4 of our Atlassian model: 21 of 25 apps compile, and the loop that was a diagram
ArticleLocal AI

v0.4 of our Atlassian model: 21 of 25 apps compile, and the loop that was a diagram

Mihai Perdum12 min read
I taught a 27B model to write Forge apps. As far as I can find, nobody had done that before
ArticleLocal AI

I taught a 27B model to write Forge apps. As far as I can find, nobody had done that before

Mihai Perdum11 min read