PulseAugur
EN
LIVE 11:34:07

Qwen3.8-Flash-Next-oQ4e-mtp model runs locally on Apple M3 Max, impresses user

By PulseAugur Editorial · [1 sources] ·

A user on Mastodon shared their experience running the Qwen3.8-Flash-Next-oQ4e-mtp model locally on their Apple M3 Max chip. Despite slow performance due to only being able to offload 50% of the model's experts, the user was impressed that it successfully completed a benchmark for computer use with a custom GUI and harness, scoring 23 out of 25. This model is noted as the first local model the user could run that was capable of tackling this specific benchmark. AI

IMPACT Demonstrates the increasing capability of local LLMs on consumer hardware, potentially enabling more widespread use cases.

RANK_REASON User experience report on running a specific model locally on consumer hardware.

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Qwen3.8-Flash-Next-oQ4e-mtp model runs locally on Apple M3 Max, impresses user

How we ranked this

Signal score
12 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
User experience report on running a specific model locally on consumer hardware.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · chikim ·

    😲 OMG, # Qwen3 .8-Flash-Next-oQ4e-mtp on oMLX is the first local model I could run on my M3 Max 64 GB that could tackle my benchmark for # ComputerUse with cust

    😲 OMG, # Qwen3 .8-Flash-Next-oQ4e-mtp on oMLX is the first local model I could run on my M3 Max 64 GB that could tackle my benchmark for # ComputerUse with custom GUI and custom harness. It scored 23/25! It's very slow on my machine, with prompt processing at 201.3 tok/s and toke…

RELATED ENTITIES

RELATED TOPICS