qwen38-27b-mlx-mtp-recipe
qwen38-27b-mlx-mtp-recipe is M4 Max 128GB: Qwen3.8-27B 8-bit MLX native MTP recipe, measured DFlash2 comparison and concurrency caveats - Weschera/qwen38-27b-mlx-mtp-recipe. It is ranked #1236 on the Dev Radar, in Other, first seen 12 days ago and shared in 1 post (7.3k views).
GitHub - Weschera/qwen38-27b-mlx-mtp-recipe: M4 Max 128GB: Qwen3.8-27B 8-bit MLX native MTP recipe, measured DFlash2 comparison and concurrency caveats · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Weschera / qwen38-27b-mlx-mtp-recipe Public Notifications You must be signed in to change notification settings Fork 0 Star 1…
What people said about qwen38-27b-mlx-mtp-recipe on X
Qwen3.8-27B Uncensored @OrcaRouter on my M4 Max, 128GB recipe Both MLX quants with native MTP: 4-bit: 42.2–44.3 tok/s 8-bit: 32.3–32.4 tok/s ~34% higher throughput at 4-bit in this prose test. Recipe + raw results: https://github.com/Weschera/qwen38-27b-mlx-mtp-recipe
— @WescheNex1q, 12 days ago · 35 likes · see the post
Alternatives to qwen38-27b-mlx-mtp-recipe
- Ling-3.0-flash-Fin — Qwen-Drive-1.0-4B is a vision-language foundation model that handles 3D perception, driving VQA, and motion planning…
- Cactus Compute — It runs on mobiles, wearables, smart home devices, small robots and microcontrollers, with prebuilt engines for macOS,…
- bespoke-nimble-9b — We’re on a journey to advance and democratize artificial intelligence through open source and open science.
- orcabonsai-27b-uncensored — Open source
- glm-5.3-flash-exl3-2x-dgx-sparks — GLM-5.3 Flash EXL3 for 2-4x DGX Sparks. Contribute to MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks development by…
- deepseek-v4.1-flash — Original safetensors
qwen38-27b-mlx-mtp-recipe in numbers
- Rank on the Dev Radar: #1236 of 1578
- Shared in 1 post by 1 account: @WescheNex1q
- 7.3k views on those posts
- First seen 12 days ago, last shared 12 days ago
- Pricing seen by Jev: open source
- Market: Other
FAQ
What is qwen38-27b-mlx-mtp-recipe?
M4 Max 128GB: Qwen3.8-27B 8-bit MLX native MTP recipe, measured DFlash2 comparison and concurrency caveats - Weschera/qwen38-27b-mlx-mtp-recipe It was first shared on X 12 days ago and is ranked #1236 on the Dev Radar.
Is qwen38-27b-mlx-mtp-recipe free?
It is open source.
Who shared qwen38-27b-mlx-mtp-recipe?
1 account on X, including @WescheNex1q, in 1 post totalling 7.3k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 14.4k posts from 4.7k X accounts over the last 21 days, 1.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.