deepseek-v4.1-flash-exl3-2x-dgx-sparks
deepseek-v4.1-flash-exl3-2x-dgx-sparks is DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks - MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks. It is ranked #54 on the Dev Radar, in Other, first seen 6 days ago and shared in 4 posts (62.7k views).
GitHub - MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks: DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks · 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 }} MiaAI-Lab / DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks Public Notifications You must be signed in to change notification settings Fork 30 Star 219 main Branches Tags Go to…
What people said about deepseek-v4.1-flash-exl3-2x-dgx-sparks on X
You can do it too. Run DeepSeek v4.1 Flash locally: - 2x DGX Sparks ~50 tok/s on prose. - Smooth as a butter. https://github.com/MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks
— @MiaAI_lab, 3 days ago · 394 likes · see the post
You can run it too, easily. DeepSeek v4.1 Flash for 2x DGX Sparks Buttery smooth experience. https://github.com/MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks
— @MiaAI_lab, 1 days ago · 163 likes · see the post
DeepSeek V4.1 Flash tp2, beat tp4 in our benchmark, and the winning deployment used a smaller quant. Mia TP2 EXL3: 91.2/100 Mia TP4: 87.7/100 Same frozen benchmark: 76 scenarios × 2 repeats, thinking OFF, uncapped output, one request at a time. Why might the smaller quant win? We changed more than the number of…
— @WescheNex1q, 4 days ago · 88 likes · see the post
Alternatives to deepseek-v4.1-flash-exl3-2x-dgx-sparks
- 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
deepseek-v4.1-flash-exl3-2x-dgx-sparks in numbers
- Rank on the Dev Radar: #54 of 1578
- Shared in 4 posts by 3 accounts: @MiaAI_lab, @WescheNex1q, @plotarmordev
- 62.7k views on those posts
- First seen 6 days ago, last shared 1 days ago
- Pricing seen by Jev: open source
- Market: Other
FAQ
What is deepseek-v4.1-flash-exl3-2x-dgx-sparks?
DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks - MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks It was first shared on X 6 days ago and is ranked #54 on the Dev Radar.
Is deepseek-v4.1-flash-exl3-2x-dgx-sparks free?
It is open source.
Who shared deepseek-v4.1-flash-exl3-2x-dgx-sparks?
3 accounts on X, including @MiaAI_lab, @WescheNex1q, @plotarmordev, in 4 posts totalling 62.7k 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.