Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
mitkox 
posted an update 5 days ago
Post
1419
GLM-4.7-Flash is fast, good and cheap.
3,074 tokens/sec peak at 200k tokens context window on my desktop PC.
Works with Claude Code and opencode for hours. No errors, drop-in replacement of the Anthropic cloud AI.
MIT licensed, open weights, free for commercial use and modifications.
Supports speculative decoding using MTP, which is highly effective in mitigating latency.
Great for on device AI coding as AWQ 4bit at 18.5 GB. Hybrid inference on a single consumer GPU + CPU RAM.
unmodeled-tyler

"good, fast, and cheap" are the magic words!

·
double-brown

Usually it's a case of choose two
ProgramerSalar

Fast, capable, and truly open — it hits a rare trifecta. With a 200k context window, peak throughput over 3k tokens/sec, and full MIT-licensed open weights for commercial use, it’s a serious drop-in replacement for cloud APIs like Claude.

In this post