nanbeige4.3-33b-w4a16-2x-rtx-3090
nanbeige4.3-33b-w4a16-2x-rtx-3090 is Nanbeige4.3-33B int4 (AutoRound W4A16) on 2x RTX 3090 in vLLM: recipe, C1-C6 bench, 69-scenario eval - tonyd2wild/Nanbeige4.3-33B-W4A16-2x-RTX-3090. It is ranked #707 on the Dev Radar, in AI dev tools, first seen 4 days ago and shared in 2 posts (9.1k views).
GitHub - tonyd2wild/Nanbeige4.3-33B-W4A16-2x-RTX-3090: Nanbeige4.3-33B int4 (AutoRound W4A16) on 2x RTX 3090 in vLLM: recipe, C1-C6 bench, 69-scenario eval · 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 }} Repository navigation Nanbeige4.3-33B-W4A16-2x-RTX-3090 Public Notifications You must be signed in to change notification…
What people said about nanbeige4.3-33b-w4a16-2x-rtx-3090 on X
🔧 Nanbeige4.3-33B dropped with no int4 that vLLM can run on RTX 3090s. So we made one. 📦 Full recipe: AutoRound W4A16 quant, vLLM launcher, C1-C6 bench, 69-scenario eval 🖥️ 2x RTX 3090, NVLink, TP2 ⚡ 66 tok/s single stream https://github.com/tonyd2wild/Nanbeige4.3-33B-W4A16-2x-RTX-3090
— @Tech2Wild, 4 days ago · 47 likes · see the post
🧠 Nanbeige4.3-33B int4 weights are live on Hugging Face 🗜️ 66 GB down to 20.8 GB (AutoRound W4A16, GPTQ format) 🖥️ Runs on two 24 GB cards in vLLM with Marlin kernels 📏 128K context, 213K-token KV pool 🔓 Apache 2.0 https://huggingface.co/Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound
— @Tech2Wild, 4 days ago · 20 likes · see the post
Alternatives to nanbeige4.3-33b-w4a16-2x-rtx-3090
- goo.gle — Officially in beta, the AppFunctions API is opening up powerful new ways to integrate your functionality.
- Kimi AI with K3.1 Pro — Try Kimi K3.1 Pro to tackle complex coding projects, build 3D models, conduct financial research, and take on more…
- Agents in flight — Give it a try
- Baseten — This session is our most in-demand yet. See you there
- project-maya — Checkout Maya
- deepinfer — You gotta love Deepseek. This is awesome stuff!
nanbeige4.3-33b-w4a16-2x-rtx-3090 in numbers
- Rank on the Dev Radar: #707 of 8798
- Shared in 2 posts by 1 account: @Tech2Wild
- 9.1k views on those posts
- First seen 4 days ago, last shared 4 days ago
- Pricing seen by AGK Intelligence: open source
- Market: AI dev tools
FAQ
What is nanbeige4.3-33b-w4a16-2x-rtx-3090?
Nanbeige4.3-33B int4 (AutoRound W4A16) on 2x RTX 3090 in vLLM: recipe, C1-C6 bench, 69-scenario eval - tonyd2wild/Nanbeige4.3-33B-W4A16-2x-RTX-3090 It was first shared on X 4 days ago and is ranked #707 on the Dev Radar.
Is nanbeige4.3-33b-w4a16-2x-rtx-3090 free?
It is open source.
Who shared nanbeige4.3-33b-w4a16-2x-rtx-3090?
1 account on X, including @Tech2Wild, in 2 posts totalling 9.1k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 20:27 UTC. Full method.