Tag

#Open-Weight LLMs

Every article tagged #Open-Weight LLMs.

2 articles

Mistral Medium 3.5 Self Host: 77.6% SWE-Bench on 4 GPUs (2026)

JUL 20, 202613 min read

Mistral Medium 3.5 Self Host: 77.6% SWE-Bench on 4 GPUs (2026)

Mistral Medium 3.5 is the 128B open-weight coding model launched April 29, 2026 with 77.6% SWE-Bench Verified and 256K context.

Local Agentic Coding May 2026: Qwen 3.6 + BeeLlama.cpp + Star Elastic

JUL 19, 202614 min read

Local Agentic Coding May 2026: Qwen 3.6 + BeeLlama.cpp + Star Elastic

Run a real agentic coding stack on a single 24 GB GPU in May 2026: Qwen 3.6 27B at 262K context, BeeLlama.