Compare model versions

Diff

Before

*Tiel* is the fast coder of the arsenal. At 4-bit quantization and 21 GB it fixes real codebase issues at the rate (and speed, with
the right GPU) of Opus 4.6 medium, while holding the best multi-turn conversation of any local model we
have measured. It is also cheerfully bad at trivia.

Pick it for work. Pick something else for exams.

> **This is [Ornith-1.5-35B-A3B](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B) re-quantized
> with oMLX's oQ4e quantizer and carrying the [Sharp chat template](https://huggingface.co/peculiar-ragdoll/Qwen-Sharp-Chat-Templates)**
> inside the checkpoint. For speculative decoding, the [identical build with Ornith's trained MTP head](https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-MLX-oQ4e-MTP) is a separate repo — the same weights plus the head, for runtimes that can use it.

After

*Tiel* is the fast coder of the arsenal. At 4-bit quantization and 21 GB it fixes real codebase issues at the rate (and speed, with
the right GPU) of Opus 4.6 medium, while holding the best multi-turn conversation of any local model we
have measured. It is also cheerfully bad at trivia.

Pick it for work. Pick something else for exams.

> **This is [Ornith-1.5-35B-A3B](https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B) re-quantized
> with oMLX's oQ4e quantizer and carrying the [Sharp chat template](https://huggingface.co/peculiar-ragdoll/Qwen-Sharp-Chat-Templates)**
> inside the checkpoint. For speculative decoding, the [identical build with Ornith's trained MTP head](https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-MLX-oQ4e-MTP) is a separate repo.
> **The uncensored and improved CyberTiel is out now!** [Get it here](https://huggingface.co/peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-MLX-oQ4e).