Qwen 3.8 27B at 48-65 tok/s on a Mac Studio M4 Max — measured oMLX native-MTP recipe, same-day A/B vs mlx-vlm+MTP sidecar, raw benchmark JSON included
☆71Aug 21, 2026Updated 2 months ago
Alternatives and similar repositories for Qwen3.8-27B-oMLX-MTP-Mac
Users that are interested in Qwen3.8-27B-oMLX-MTP-Mac are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 1.0 Beta · oMLX 0.6.3rc2 Dual-ANE+CPU · Qwen3.8-27B abliterated oQ4e · Mac Studio M3 Ultra☆44Aug 23, 2026Updated 2 months ago
- Three-DGX-Spark TP3 serving recipe for GLM-5.3 Flash☆21Oct 5, 2026Updated last month
- ☆28Sep 13, 2026Updated last month
- ☆10Jan 27, 2022Updated 4 years ago
- Independent local Stream Deck Plus companion for the Codex desktop app.☆18Oct 21, 2026Updated 2 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆17Sep 29, 2026Updated last month
- A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from f…☆33Updated this week
- wireguard代码阅读笔记，wireguard代码详解☆12Jun 13, 2024Updated 2 years ago
- 微信多开管理器☆12Jun 17, 2025Updated last year
- Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gem…☆735Oct 5, 2026Updated last month
- The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B…☆2,673Updated this week
- A local inference engine for Apple silicon, built around the model.☆2,110Updated this week
- Classify data center IP addresses from cloud providers☆15May 10, 2022Updated 4 years ago
- MiniMax M2.7 NVFP4 dual-GB10 Blackwell benchmark: vLLM FlashInfer-CUTLASS, public data, HTML canvas report, and Docker runtime.☆13May 24, 2026Updated 5 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Build, load, and verify NCCL for switchless DGX Spark RoCE cycles☆21Oct 25, 2026Updated last week
- 💬 Chat with your Database ✨☆14May 20, 2025Updated last year
- DWM (Domain Weight Modification) by Blackfrost_AI — self-instructing runbook package for Qwen 9B-class models and their fine-tunes☆15Oct 5, 2026Updated last month
- Local LLM benchmark tool for comparing engines (MLX vs llama.cpp), scenarios on Apple Silicon☆25Sep 11, 2026Updated last month
- LLM Inference Engine for Metal, CUDA and Vulkan.☆1,677Updated this week
- ☆10Jul 1, 2025Updated last year
- Z Agent — agent-orchestration runtime for Z-Lab robots: plan/route/verify/recover. NL in, verified robot behavior out. Fork of vector-os-…☆11Jul 30, 2026Updated 3 months ago
- 3D models for DGX cases☆54Aug 14, 2026Updated 2 months ago
- Full GLM-5.3 (753B) served by TensorFold with tensor parallel 4 across four NVIDIA DGX Sparks: results, recipe, node settings, benches☆22Oct 13, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Provisioning, Lifecycle and Platform Management Group☆21Apr 28, 2026Updated 6 months ago
- a curated paper list for code as policy in robot learning☆18Jun 24, 2026Updated 4 months ago
- Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with c…☆2,389Updated this week
- A graph knowledge base implemented in neo4j.☆12Jul 3, 2018Updated 8 years ago
- Sushi engine runs very high quality quant model in Apple Silicon, using both STQ and EXL3 format with special tuning technology.☆421Updated this week
- Full GLM-5.3 (753B, Int4-Int8Mix) on 4x NVIDIA DGX Spark, vLLM TP4☆23Oct 13, 2026Updated 3 weeks ago
- @jmorganca's ollama.ai demo app on Fly.io☆17Dec 5, 2024Updated last year
- ☆11Feb 4, 2020Updated 6 years ago
- What's is Hyperaudio? How do I get started?☆11Jan 26, 2023Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Apple Silicon GPU DVFS reverse engineering: voltage corners, CLPC frequency control, Metal benchmarks☆71Oct 30, 2026Updated last week
- ROS 2 Jazzy autonomy stack for a mecanum-wheeled platform, extended as a bridge between Habitat and the real robot. Converts panoramic im…☆17Jul 16, 2026Updated 3 months ago
- Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a sep…☆49Jul 7, 2026Updated 3 months ago
- ☆21Feb 22, 2022Updated 4 years ago
- The 8th Wall code archive.☆20May 26, 2026Updated 5 months ago
- ☆68Jun 4, 2026Updated 5 months ago
- Quick-start guides, helper code, tips and tricks for use in MTRX5700 @ The University of Sydney. Copyright.☆15Mar 5, 2025Updated last year