🧰 GGUF

The items that name it 49

• [AINews] Google admits AI Mode hurts Search revenue; -15% $500B drop worst since 2004 IPO. AI Bear Market coming?
  articleas classification.technologies2026-10-31
• nemotron-halloween
  writeupas classification.technologies2026-10-30
• [AINews] Building AIE CODE: The top Coding Agent Conference
  articleas classification.technologies2026-10-30
• Welcome Le Chonk: Mistral Large 4 on Hugging Face
  articleas classification.technologies2026-10-29
• Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms
  articleas classification.technologies2026-10-29
• [AINews] Anthropic files for $2T IPO in 2 weeks: 1400% growth rate, 48% of revenue through cloud partners, 85% margin, $1B op profit in Q2, $134B cash in bank and $10B lifetime burn
  articleas classification.technologies2026-10-27
• Syb (@DegenOfWallSt) on X
  threadas frameworks and tools2026-10-25

  Quantised format; community GGUF quants of the model are available.

• [AINews] Black October
  articleas classification.technologies2026-10-23
• Latest open artifacts (#25): DeepSeek V4.1 Flash 1017, American-made models, and new regulatory controls in the US & China
  articleas classification.technologies2026-10-20
• [AINews] not much happened today
  articleas classification.technologies2026-10-20
• [AINews] not much happened today
  articleas classification.technologies2026-10-20
• AnyLanguageModel 1.0: One Year of Local Models on Apple Platforms
  articleas classification.technologies2026-10-20
• Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console
  repoas classification.technologies2026-10-16
• [AINews] Agents disprove Polysemanticity; greatly improve Interpretability & Alignment
  articleas classification.technologies2026-10-16
• Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta
  articleas classification.technologies2026-10-15
• LFM2.5-24B-A2B: Built for fast on-device agents
  articleas classification.technologies2026-10-14
• [AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
  articleas classification.technologies2026-10-13
• JASON MCNAB (@JASONMCNAB) on X
  threadas frameworks and tools2026-10-09

  Quantised model file format in which the 4-bit POCKET-Darwin-180B is released.

• [AINews] not much happened today
  articleas classification.technologies2026-10-08
• The model that didn't exist, so you made it yourself
  articleas frameworks and tools2026-10-08

  File format used to ship the Pocket Rewriter 0.8B student (as an 812 MB file) for running on a CPU.

• I'm not paying $20 for ChatGPT or Claude because a free local LLM does
  articleas classification.technologies2026-10-07
• [AINews] Quasi-Riemann-Hypothesis: OpenAI publishes 722 math papers solving 90 of the top 500 open math problems; “the most significant moment” in >100 years of mathematics
  writeupas classification.technologies2026-10-07
• Qwen3.8 27B addition in words
  writeupas classification.technologies2026-10-04
• [AINews] not much happened today
  articleas classification.technologies2026-10-03
• From the creator of Redis; run LLM locally with ds4
  toolas classification.technologies2026-10-02
• [AINews] Gemini 4 Argon: GDM’s answer to Astra/Fable, with 1M output
  articleas classification.technologies2026-10-01
• StartLuxLabs/StartLux-Decision
  repoas frameworks and tools2026-09-29

  Quantized model format; Q8_0 and Q4_K_M builds are discussed.

• Uncensored and Offensive Security AI Models Benchmark
  repoas classification.technologies2026-09-29
• [AINews] Opus 5.5 is good at explainer videos
  articleas classification.technologies2026-09-29
• Holo4: powering generalist computer-use agents
  articleas classification.technologies2026-09-28
• [AINews] The Future of Latent Space
  articleas classification.technologies2026-09-25
• LFM2.5-VL-3B-DSpark (Liquid AI)
  articleas classification.technologies2026-09-24
• [AINews] Claude Opus 5.5, the new default model for AINews — and everybody cuts prices 40-50%
  articleas classification.technologies2026-09-23
• Transformers now runs llama.cpp quants
  articleas frameworks and tools2026-09-22

  File format developed by the llama.cpp team that packages model weights and metadata, including tokenizer information and an optional chat template, in one file, supporting different quantization levels.

• [AINews] not much happened today
  articleas classification.technologies2026-09-18
• OmniJev/awesome-jev-gallery
  repoas classification.technologies2026-09-17
• AnotiaWang/awesome-decision-models
  repoas classification.technologies2026-09-17
• [AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
  writeupas classification.technologies2026-09-17
• Mapika/decider
  repoas classification.technologies2026-09-16
• bilibili/Index-Translate
  repoas classification.technologies2026-09-15
• Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
  writeupas classification.technologies2026-09-03
• Nehanth/pooled
  repoas classification.technologies2026-09-01
• Granite 4.2 LLMs: How They're Built
  articleas classification.technologies2026-08-25
• Up to 3.2x Faster Inference with LFM2.5-DSpark
  articleas classification.technologies2026-08-20
• Unsloth AI (@UnslothAI) on X
  threadas classification.technologies2026-07-31
• deepbeepmeep/Wan2GP
  repoas frameworks and tools2026-07-30

  A quantized checkpoint format; GGUF CUDA kernels (e.g. 1.0.25) accelerate speculative decoding for Q4_K and Bonsai PTQ1_0 without extra VRAM.

• ThorOdinson246/whatisit-nl2sh
  repoas classification.technologies2026-07-29
• Kyutai Pocket TTS
  repoas classification.technologies
• Ternary-Bonsai-2-27B: 27B model compressed to ~1.75 bits/weight, 98.2% of FP16 quality retained
  repoas classification.technologies