Model Releases
Benchmarked @DJLougen ’s Ornstein-27B-v2 Q6_K on my RTX 3090 using hermes-bench, my new open-source benchmarking UI for local LLMs and Herme…
Benchmarked @DJLougen ’s Ornstein-27B-v2 Q6_K on my RTX 3090 using hermes-bench, my new open-source benchmarking UI for local LLMs and Hermes agents. Ornstein is a Qwen 3.5 27B fine-tune trained on re
Benchmarked @DJLougen ’s Ornstein-27B-v2 Q6_K on my RTX 3090 using hermes-bench, my new open-source benchmarking UI for local LLMs and Hermes agents. Ornstein is a Qwen 3.5 27B fine-tune trained on reasoning traces filtered through a Drift Diffusion Model pipeline. Quality over quantity. The DDM separates “fake” reasoning (hedging, restating, circling) from the real thing with >99% sensitivity. Running llama.cpp + TurboQuant turbo3_tcq KV compression. LLM-as-judge scoring via Carnice-9b. Real tool calls, real execution, no synthetic evals. 12 tasks across two suites. Results thread below. 🧵 Model: http://huggingface.co/DJLougen/Ornstein-27B-v2-GGUF
Source: Clem Delangue (X) | 2026-04-13