exllamav3
exllamav3 is One-line default flip. Measured +7 to +13% across three prompt classes on GB10 with acceptance unchanged (#2); the kernels keep fp16 arithmetic and reduction order so storage rounding is the only d.... It is ranked #331 on the Dev Radar, in Other, first seen 1 days ago and shared in 1 post (33.1k views).
hc_mix: EXL3_GR_INT8 default on by vcruz305 · Pull Request #3 · vcruz305/exllamav3 · 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 }} vcruz305 / exllamav3 Public forked from turboderp-org/exllamav3 Notifications You must be signed in to change notification settings Fork 0 Star 0 hc_mix: EXL3_GR_INT8 default on - # 3 # 3 Merged…
What people said about exllamav3 on X
Qwen3.8-Flash-Next -> 79.95 tok/s. 🔥 ONE DGX Spark. Full 262K cache configured. 🚀 Qwen3.8-Flash-Next EXL3 just got another major update. New measured default: MTP ndt=5 DSpark, dc=0.6 8-bit KV 262,144-token cache At an actual 240K-token prompt: 72.0 tok/s decode ~1,150 tok/s prefill Exact needle retrieval 𝗙𝗣𝟭𝟲…
— @ViC305, 1 days ago · 263 likes · see the post
Alternatives to exllamav3
- 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…
- bespoke-nimble-9b — We’re on a journey to advance and democratize artificial intelligence through open source and open science.
- Cactus Compute — It runs on mobiles, wearables, smart home devices, small robots and microcontrollers, with prebuilt engines for macOS,…
- orcabonsai-27b-uncensored — Open source
- Spark-X2.5 — 🤖 ModelScope
- grok.com —
exllamav3 in numbers
- Rank on the Dev Radar: #331 of 1353
- Shared in 1 post by 1 account: @ViC305
- 33.1k views on those posts
- First seen 1 days ago, last shared 1 days ago
- Pricing seen by Jev: open source
- Market: Other
FAQ
What is exllamav3?
One-line default flip. Measured +7 to +13% across three prompt classes on GB10 with acceptance unchanged (#2); the kernels keep fp16 arithmetic and reduction order so storage rounding is the only d... It was first shared on X 1 days ago and is ranked #331 on the Dev Radar.
Is exllamav3 free?
It is open source.
Who shared exllamav3?
1 account on X, including @ViC305, in 1 post totalling 33.1k 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. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:06 UTC. Full method.