Hackernews posts about gguf

  1. GLM-5.3-Flash-GGUF (huggingface.co)
    9 points by walrus01 22 days ago | 1 comments
  2. Unsloth/Qwen3.8-Flash-Next-GGUF (huggingface.co)
    9 points by Philpax 25 days ago | discuss
  3. Xyntetik Runner – a GGUF runtime in plain C that proves what it runs (github.com)
    7 points by JoakimPalm-Zen 26 days ago | discuss
  4. Axera AX8850 LLM running ggufs (github.com)
    5 points by woolcoxm 25 days ago | discuss
  5. GLM5.3 unsloth GGUFs are now up (huggingface.co)
    4 points by walrus01 23 days ago | 1 comments
  6. Per-tensor layout maps for GGUF quantization (huggingface.co)
    3 points by pickledish 8 days ago | discuss
  7. Gguf: Harden loader against malformed tensor dims and metadata types (github.com)
    3 points by gzxharrison001 25 days ago | discuss
  8. Ternary-Bonsai-8B-Gguf (huggingface.co)
    2 points by Bluestein about 6 hours ago | discuss
  9. Show HN: Single-File GGUF Inference (wasm-gguf.netlify.app)
    1 points by badfox 18 days ago | discuss
  10. Fuzzy terminal manager to pick, configure, and run local GGUF models (github.com)
    1 points by modinfo 23 days ago | discuss
  11. Show HN: Swift-Qwen3.8-27B, -58.3% thinking, x1.95 speed, accuracy of xhigh (huggingface.co)
    30 points by kisjovan 4 days ago | 17 comments
  12. I've tested some local LLMs on prosumer hardware, here are some findings
    7 points by felineflock 28 days ago | discuss
  13. Show HN: Jinfer – AI inference engine for the JVM. AI in a jar (qxotic.ai)
    5 points by mukel 5 days ago | 1 comments
  14. Show HN: PicoLM v1.0-rc1 (github.com)
    3 points by gabucino 17 days ago | discuss
  15. Hi HN
    2 points by DEVGUSTAVOSIS 1 day ago | 1 comments
  16. Show HN: Local audit trail for Claude Code tool calls (github.com)
    1 points by zaghaghi 14 days ago | discuss
  17. Qwen3.8-Flash-Next non-uniform quantization runs on 2 RTX3090s (huggingface.co)
    9 points by pfeifferj 6 days ago | 2 comments
  18. Nemotron 3.5 Lightning-Omni: I gave NVIDIA's agent model eyes and ears (huggingface.co)
    1 points by vkaufmann 26 days ago | discuss
  19. Show HN: Find the cheapest GPU to run your model (www.gpufind.cloud)
    3 points by the_app_guy_1 14 days ago | discuss
  20. Unsloth Dynamic 3.0 GGUFs (unsloth.ai)
    322 points by jonesy827 about 1 month ago | 119 comments
  21. Unsloth Dynamic 2.0 GGUFs (unsloth.ai)
    237 points by tosh 7 months ago | 68 comments
  22. What's in a GGUF, besides the weights – and what's still missing? (nobodywho.ooo)
    195 points by bashbjorn 4 months ago | 58 comments
  23. Ollama and gguf (github.com)
    173 points by indigodaddy about 1 year ago | 91 comments
  24. Unsloth Qwen3.8-27B GGUF files (huggingface.co)
    69 points by apitman about 1 month ago | 5 comments
  25. MDST Engine: run GGUF models in the browser with WebGPU/WASM (mdst.app)
    33 points by vmirnv 7 months ago | 12 comments
  26. Show HN: Quant Picker – which GGUF file fits your model and machine (vettedconsumer.com)
    20 points by ermantrout 3 months ago | discuss
  27. Ollama can run any GGUF Model on Hugging Face Hub now (huggingface.co)
    15 points by djhu9 almost 2 years ago | 1 comments
  28. Show HN: Llama.cpp Tutorial 2026: Run GGUF Models Locally on CPU and GPU
    13 points by anju-kushwaha 5 months ago | 4 comments
  29. I packed 16 GB of GGUF quants into 1.8 GB, losslessly (github.com)
    12 points by adamdanielsson1 3 months ago | 6 comments
  30. Show HN: RunNburn – Run a 295B Moe from a 98GB GGUF on a 64GB RAM Desktop (github.com)
    11 points by coderredlab about 2 months ago | discuss
  31. Benchmark GGUF model with ONE line of code (github.com)
    6 points by alanzhuly almost 2 years ago | 1 comments
  32. Qwen3.5 GGUF Benchmarks (unsloth.ai)
    5 points by tosh 7 months ago | discuss
  33. How to manipulate running LLM outputs via GGUF page cache poisoning (github.com)
    4 points by piotrbednarsalt 7 months ago | 1 comments
  34. GGUF Quantization Compared: Q4_K_M vs. IQ4_XS vs. IQ4_NL (kaitchup.substack.com)
    4 points by peter_d_sherman about 1 month ago | discuss
  35. Choosing a GGUF Model: K-Quants, IQ Variants, and Legacy Formats (kaitchup.substack.com)
    4 points by theanonymousone 3 months ago | discuss
  36. GGUF vs. MLX when to choose what when running Local LLMs (muhammadraza.me)
    4 points by mr_o47 4 months ago | discuss
  37. Choosing a GGUF Model: K-Quants, IQ Variants, and Legacy Formats (kaitchup.substack.com)
    4 points by theanonymousone 8 months ago | discuss
  38. Show HN: Run Unsloth Dynamic GGUFs using Docker model runner (github.com)
    3 points by ericcurtin 10 months ago | 1 comments
  39. Unsloth/DeepSeek-V4-Pro-0813-GGUF (huggingface.co)
    3 points by asoberbeck about 1 month ago | discuss
  40. KoboldCPP: Run GGUF Models Easily with a KoboldAI UI. One File. Zero Install (github.com)
    3 points by theanonymousone 3 months ago | discuss
  41. Ollama v0.30.0-rc23: "directly support llama.cpp" & "compatibility with GGUF" (github.com)
    3 points by theanonymousone 4 months ago | discuss
  42. Tq-KV – Rust implementation of TurboQuant that works on GGUF models
    3 points by onurgokyildiz 6 months ago | discuss
  43. Show HN: Host any GGUF model in one command (github.com)
    3 points by gauravvij137 6 months ago | discuss
  44. GGML GGUF File Format Vulnerabilities (www.databricks.com)
    3 points by eatonphil 7 months ago | discuss
  45. Unsloth Dynamic GGUFs DeepSeek (671B) outperforms SOTA models (docs.unsloth.ai)
    3 points by frainfreeze about 1 year ago | discuss
  46. Unsloth Dynamic 2.0 GGUFs (docs.unsloth.ai)
    3 points by serialx about 1 year ago | discuss
  47. DeepSeek-R1 on iPhone? (DeepSeek-R1-Distill-Qwen-1.5B-GGUF) (huggingface.co)
    3 points by ralphsebastian over 1 year ago | discuss
  48. Show HN: Shimmytok – Pure Rust GGUF tokenizer (no C++, no extra files) (github.com)
    2 points by MKuykendall 8 months ago | 2 comments
  49. Ask HN: Are third party gguf/mmproj safe on Llama in production env
    2 points by skye0110 about 1 month ago | discuss