0xSero
Importance score: 10 • Posted: Unknown
Score
10
@neza_zeza retweeted Best models to run on your hardware:—— 64 GB ——Qwen3-coder-next-80B-4bit (coding, Claude code, general agent) Qwen3.5-122B-reap: (browser use, multimodal, tool calling, general agent) —— 96 GB ——GLM-4.6V (multimodal and tool calls)Hermes-70B (Jailbroken)Nemotron-120B-Super: (openclaw)Mistral-4-Small (general agent)—— 192 GB ——All these are excellent top tier LLMs and approach sonnet in capabilities Step-3.5-FlashQwen3.5-397B-REAPMiniMax-M2.5 (soon M2.7)GLM-4.7-Reap 0xSero @0xSero Best models to run on your hardware levelI'll be doing this every week, I hope you guys enjoy.---- 8 GB ----Autocomplete for coding (like Cursor Tab)- huggingface.co/NexVeridian/ze…- huggingface.co/bartowski/zed-…Tool calling, assistant style - huggingface.co/nvidia/NVIDIA-…---- 16 Gb ----Here things get better:Multimodal- https://t.co/WNwxTttMQC- https://t.co/1U5HR9iWRX- https://t.co/OiOkDoahZ8---- 24 GB ----The best model you can get (thanks Qwen) https://t.co/fy8INjJP8NGreat model (strong agents) https://t.co/CRpiKlSX5dMine hehe https://t.co/YBeUveU0M6I'm doing a weekly series Posted Mar 28, 2026 at 10:22AM Posted Mar 28, 2026 at 10:33PM
Likes
0
Reposts
0
Views
0