Is Qwen 3.8 27b really that good?
Local LLMs do a lot of work for me. I love them. Saved me and my clients a lot of money, but not every one is useful. They handle various automations, among other things, video transcription, voiceover generation, and network security. To find
Gemini 3.7 Flash
GLM 5.3 Grok 4.6 Qwen 3.8 Max GLM 5.3 isn't bad, but It falls behind the similarly priced and faster Grok 4.6.
DeepSeek V4 Pro GLM 5.3
Kimi K3 Qwen 3.8 Max GLM 5.3 is not close to Kimi K3, but Considering the price, it is a good model.
I swear I was shocked by what I saw. Qwen 3.8 27B Q4 is now running on an RTX 4060 with 8GB VRAM only, and it is unlocked...
I swear I was shocked by what I saw. The Qwen 3.8 27B Q4 is now running on an RTX 4060 with only 8GB VRAM, and it has a window of 64,000 tokens open, which after showing its size on the disk only takes 14.6GB thanks to the new IQ4_XS technology from Unsloth. ← Generation speed is 150 tokens per second, and reading is 5 tokens per second...
You have reached the end of the archive
All of qwen38