Well I can officially say I got a local 744b model running 😂
470 036 sat
Post by $bender ✪
That was a long grueling test ... Threw the same question at qwen 3.8:28 fully in vram, it smoked it answer wise... And took 10 seconds versus an hour for 500 tokens 😂 but it was a good experiment and I got a good blog write up on it .
What the chain says
- Block
- 964 211
- Time
- 2026-08-28T00:13:48Z
- Signer
- 1xELcaMVpxdzSV3w2bMwgbJdMKq3xmgcu
- App
- twetch
- Type
- reply
- Content type
- text/markdown
Fields the transaction did not carry are omitted. Open the payload to see the bytes as stored.
Signed by
1xELcaMVpxdzSV3w2bMwgbJdMKq3xmgcu UnverifiedReplies (3)
Also learned I can get 17-20 tok/s with gpt-oss-120b with ngl 99 and CPU moe at 28 on 5900x CPU / nvme drive and 3090 GPU... Good day... Back to qwen 3.8:28b as my daily driver tho... Lol 😂 at least I have a story to tell after all that thrashing 🤦
Ugghj 27b... Long day
Anyone wanna give this a test, I grabbed colibri from