FRAMEWIREIndonesiaUpdated Aug 19Live wire
0:00 / 0:00

Qwen 3.8 27B Q4 is now running on an RTX 4060 with just 8GB VRAM and a 64,000 token context window using Unsloth's new IQ4_XS quant at 14.6GB on disk.

→ Prefill at 150 tokens per second, decode at 5 tokens per second via native MTP → Only 25 GPU layers offloaded to stay within

0xMarioNawfalAug 1941
0:00 / 0:00

GLM 5.3 vs Gemini 3.7 Flash vs Qwen 3.8 vs Grok 4.6

Fabiano FirmoAug 191
0:00 / 0:00

Hermes Agent got Qwen 3.8 installed (with Grok)

Attached it to a Hermes Bot, and the first job I gave it was to brainstorm this animation with me for it's persona. I can't even believe this is running on my own computer. SO fast on my 5090. thanks NousResearch Teknium

Joe SparksAug 194
0:00 / 0:00

Qwen 3.8 27B running on a 3090 at Q5 just beat gemini 3.7 flash on a water surface simulation.

Same prompt, one shot, not full precision. One of the best water simulations seen across every local model tested.

0xMarioNawfalAug 1929