Sabitlenmiş Tweet
Haneul
1.5K posts
Haneul retweetledi
One of the rarer things hiding in Momo’s little world ♡
English
Haneul retweetledi
Fragments of Growth is here 🌸
A collection where every petal is a fragment of a life lived, assembled from textures captured across years of travel by @jenyavyguzov
This is just the beginning...
English
He said it wasn't his 😁
I only follow onchain, everyone needs to dyor before joining.
0x985d1f52f130c68225bc10e00af7936e358717de to 0x58028342c06c949bbd2bc5b609de452dc0edecd0
0x58028342c06c949bbd2bc5b609de452dc0edecd0 to 0xa6ad9faf65e12f55c9240ef69a20d03cec970e8f ( wl dev)
Danie.@daniennix
@CAONHTAN1 Tff😂😂 That’s not me bro
English
@johann_sath Hey mate, how many tokens did you got for $16 plan? Currently i'm using Opencode $5 plan and i'm running out of weekly credits in two days
English
GLM 5.2 for $16/mo is pretty goated
& works directly in Claude Code
life is good
English
Haneul retweetledi
GLM-5.2 is now live on Command Code!
A frontier open-source reasoning model built for long-horizon tasks.
1M context. Strong reasoning. Open source.
Available in the $1 Go plan with $10 usage credits and above!!
$ npm i -g command-code@latest
English
GLM 5.2 is now the second most used model in Command Code Go (10x credits).
English
ok tried glm 5.2 for like a whole day
replaced kimi k2.7 with glm 5.2 😩
dogfiles@0xrsydn
current daily driver update: coding - gpt 5.5 low on pi & codex harness - kimi code k2.7 on pi & opencode harness (opencode go subs) research/search in general - deepseek v4 pro on hermes harness removed anthropic subs and model completely from my current workflow china numba wan
English
Haneul retweetledi
The minimum to run the model is ~$20K in hardware and you get ~20 tok/s out
~$20K gets you around 34.6B tokens at a 12:1 input to output ratio assuming good token caching
If you ran the hardware 24/7, it would take roughly 5.5 years to break even
Jordan Nanos@JordanNanos
GLM 5.2 costs $1.40/4.40 per Mtok at 40 tok/sec and people seriously consider buying GPU rigs for it
English
Minimax m3 tokenrouter ga ada limit nya kah bang??
Di push terus ga pernah trouble
Yang belum nyobain wajib di gas sih, limited time artinya suatu saat jadi berbayar
- Regist Link:
tokenrouter.com (tanpa verif nomor tanpa verif debit card)
- Base URL: api.tokenrouter.com/v1
- Model: MiniMax-M3
Integrasi ke agent meridian mu pak GRATISSSSS
Indonesia
@MrAhmadAwais what is going on with provider api? i've got HTTP 500 lately and i couldn't access the website
English
Haneul retweetledi
@pln_123 jahat banget pln, sampe mau 5jam mati lampu:(
Indonesia
330 GB LOCAL VRAM
330 GB LOCAL VRAM
330 GB LOCAL VRAM
330 GB LOCAL VRAM
330 GB LOCAL VRAM
330 GB LOCAL VRAM
330 GB LOCAL VRAM
330 GB LOCAL VRAM
330 GB LOCAL VRAM
330 GB LOCAL VRAM
Unsloth AI@UnslothAI
You can now run Kimi K2.7 Code locally! 🌘 We shrank the 1T model to 325GB (-48%) via Dynamic 2-bit where important layers are upcasted. Run at >40 tok/s on 330GB RAM/VRAM setups. Run full precision on 610 GB. Guide: unsloth.ai/docs/models/ki… GGUF: huggingface.co/unsloth/Kimi-K…
HT
my Deepseek v4 pro api call has been slow and stucked lately anyone has the same problem? @CommandCodeAI
English
Haneul retweetledi
