GGUF

Evidence (10)

• 4Simon Willison·10/4/2026research
  Qwen3.8-27B Tested on Word-Return Addition

  Simon Willison reports an experiment running Qwen3.8-27B locally to compute sums while returning the answers in words, comparing results with and without reasoning enabled. The model was highly accurate overall, especially with reasoning on, achieving 167 correct results out of 169 attempts in the one-shot run.

• 2Hacker News·9/23/2026open_source
  Parody post shows a 25-line Python Jev classifier

  This Hacker News item presents a parody implementation of “Jev” as a small local Python script that loads a GGUF model and classifies an email into labels such as Legitimate, Spam, or Phishing. The post argues that the approach is simple, fast, and privacy-preserving because it runs locally without sending data to an external API.

• 6Hacker News·9/8/2026research
  Qwen3.8 27B 4-bit quantization keeps benchmark quality

  A benchmark comparison of Qwen3.8 27B quantizations found that the 4-bit Q4_K_M model performs essentially the same as BF16 on GPQA Diamond, IFBench, and Terminal-Bench 2.1 while using far less GPU memory. Performance drops sharply at very aggressive compression, with 1-bit quantization collapsing to near-random results on GPQA Diamond and degrading reasoning further on longer tasks.

• 7Hacker News·8/19/2026model_release
  Unsloth releases Dynamic v3.0 GGUF quants for Qwen3.8-27B

  Unsloth released Dynamic v3.0 GGUF quantizations for Qwen3.8-27B, claiming better top-1% accuracy than other providers at the same model size. The update improves calibration, layer selection, and post-training quantization methods, and is compatible with inference engines such as llama.cpp and Unsloth Desktop.

• 6Hugging Face Blog·8/19/2026model_release
  Liquid AI releases QAD Q4_0 checkpoints for LFM2.5

  Liquid AI released updated Q4_0 GGUF checkpoints for four LFM2.5 models using quantization-aware distillation. The company says the checkpoints preserve Q4_0 memory and speed while recovering most of the BF16 accuracy lost in quantization, and they are available for use with llama.cpp and other GGUF-compatible runtimes.

• 6Simon Willison·8/16/2026model_release
  Qwen 3.8 27B defaults to extreme reasoning

  Simon Willison reports that Alibaba's open-weight Qwen 3.8 27B vision model is strong, but its default xhigh reasoning setting causes very slow, token-heavy outputs on local hardware. He found that lowering or disabling reasoning effort greatly improves practical usability, while the larger Qwen 3.8 2.4T-A95B also produced a polished SVG result.

• 7The New Stack·8/12/2026model_release
  Meta ships its own distillation pipeline with Muse Glimmer

  Meta released Muse Glimmer, a 30-billion-parameter open-weight model distilled from Muse Spark and licensed under Apache 2.0. The release packages both the teacher and student sides of the distillation workflow, along with quantized builds and drafting artifacts, highlighting distillation as an enterprise deployment pipeline rather than only a model-copying concern.

• 5Hacker News·7/28/2026model_release
  Neutrino-1 8B model released with binaries and packs

  Neutrino-1 8B has been released with weights, native binaries, a GGUF pack, and an MLX pack. Users can run it through Fermion's chat tool after installing the fermion-research package, with the first run downloading and verifying a 2.56 GB transport before caching locally.

• 6Hacker News·6/29/2026model_release
  Qwen 3.6 27B as a strong local development model

  The article argues that Qwen 3.6 27B is the most compelling local model the author has tried, outperforming previous local options on constrained writing and coding tasks. It also describes how to run the model locally with llama.cpp and a GGUF quantized build from Hugging Face for interactive chat and agent workflows.

• 8Hugging Face Blog·6/2/2026model_release
  Holo3.1 Adds Local, Multienvironment Computer-Use Agents

  Hugging Face Blog announces Holo3.1, a new family of computer-use models designed to work more robustly across web, desktop, and mobile environments, with better compatibility across agent frameworks. The release also introduces quantized checkpoints such as FP8, Q4 GGUF, and NVFP4 for faster local inference on end-user devices.