Log inSign up
azael
42 posts
azael profile banner
@azaeldrm

azael

@azaeldrm
converging towards knowledge singularity.
United States
Joined March 2026
17
Following
0
Followers
RepliesRepliesRepostsRepostsMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • @azaeldrm
    azael
    @azaeldrm
    Apr 17
    Reposting for reference. This will be insane if achieved and presents easy of use and installation. Clustering my 4 homelab servers, and being able to leverage their hardware capabilities will open so many doors, plus I could hypothetically leverage all shards to perform
    @varun_mathur
    Varun
    @varun_mathur
    Apr 16
    Introducing Pods Hyperspace Pods lets a small group of people - a family, a startup, a few friends, to pool their laptops and desktops into one AI cluster. Everyone installs the CLI, someone creates a pod, shares an invite link, and the machines form a mesh. Models like Qwen 3.5
    Image
    00:00
    Readers added context
    Hyperspace Pods is not yet available for installation or use, as there are no mentions of it, model sharding, or related features in the official documentation, website, or CLI repository. hyper.space github.com/hyperspaceai/a… github.com/hyperspaceai/a…
  • @azaeldrm
    azael
    @azaeldrm
    Apr 6
    Need to migrate to Linux ASAP.
    @krishdotdev
    Kr$na
    @krishdotdev
    Apr 4
    If you are still using windows in 2026, that's a signal.
    Image
    00:00
  • @azaeldrm
    azael
    @azaeldrm
    Apr 5
    Looking forward to setting this up on my 2x3090FE homelab server. If the efficiency is true to its word, I shall reap the benefits of running much more accurate models for zero loss. Crossing my fingers.
    @loktar00
    Loktar 🇺🇸
    @loktar00
    Apr 4
    TurboQuant is getting ported to llama.cpp and if it actually delivers 6x memory compression with zero accuracy loss.... your 24GB 3090 basically becomes a 144GB card for KV cache. The local inference cost equation keeps getting more insane every week
  • @azaeldrm
    azael
    @azaeldrm
    Apr 2
    Will be trying them out asap.
    @ollama
    ollama
    @ollama
    Apr 2
    .@GoogleDeepMind Gemma 4 is here with state-of-the-art models targeting edge and workstations. Requires Ollama 0.20+ that is rolling out. 4 models: 4B Effective (E4B) ollama run gemma4:e4b 2B Effective (E2B) ollama run gemma4:e2b 26B (4B active MoE) ollama run gemma4:26b
    Image
  • @azaeldrm
    azael
    @azaeldrm
    Apr 2
    Been using v1 for the longest. Excited to try v3!
    @KyleHessling1
    Kyle Hessling
    @KyleHessling1
    Apr 2
    BIG DAY! Qwopus 27B v3 is LIVE from Jackrong! This is the third iteration from the line of the viral finetunes previously titled “Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled” It is now simply Qwopus 27B and I love the name change! On paper, the v3 is another remarkable
Advertisement
Advertisement