Models

Pinned Inexpensive LLM API providers for open source models
by Nick Antonaccio

Pinned Qwen 3.8 27b Issues
by Nick Antonaccio

Pinned GLM 5.3 Flash is the new leader in local models. And it's inexpensive+smart+fast on the API, with Opus 4.8 quality
by Nick Antonaccio

Pinned Deepseek V4 Flash is currently my favorite workhorse local model, without reservation (and it's great on the APIs too)
by Nick Antonaccio

Gemini 3.7 Flash is a real contender
by Nick Antonaccio

Testing LLMs' depth of knowledge, all the way up to Anthropic Fable
by Nick Antonaccio

Don't forget about GLM 5.2
by Nick Antonaccio

google/gemini-3.1-flash-lite-preview
by Nick Antonaccio

Ternary models
by Nick Antonaccio

Use MTP!
by Nick Antonaccio

Hy3 works locally on a single DGX Spark. It's a serious contender for best self-hosted model.
by Nick Antonaccio

Kimi K3
by Nick Antonaccio

Tencent/hy3-preview is the current medium sized model to watch
by Nick Antonaccio

GLM 5.3 may now be the best open source model
by Nick Antonaccio

Qwen 3.6 35a3b & 27b are incredible for small GPUs, Gemma 4 26a4b & 31b are runners-up
by Nick Antonaccio

Minimax M3 - my first test results with it are *Fantastic*
by Nick Antonaccio

Laguna S 2.1 is the newest great mid-size self-hostable model.
by Nick Antonaccio

arcee-ai/trinity-large-thinking
by Nick Antonaccio

Step-3.7-Flash is surprisingly good
by Nick Antonaccio

Grok 4.6 is currently one of the best frontier models
by Nick Antonaccio