mradermacher publishes GGUF quants of gemma-4-31B-it-ARA-heretic
Static GGUF files from Q2_K through Q8_0, plus mmproj supplements, are listed as the repo trends at #30.
Stories per day · 30 days
4 RSS
Relatedquantization11huggingface7deepseek4lfm32liquidai2llama-cpp2llama.cpp2local-inference2mixture-of-experts2open-weights2qwen2uncensored2abliteration1b2001coding-agents1coding-model1daslab1edge-ai1
46 stories, newest first · one card per story
Stories tagged #gguf
Scantist/GLM-5.3-SLIM-GGUF 180GB MoE model trends on Hugging Face
179.9GB version of 753B-parameter GLM-5.3 MoE drops to 563B by NAS, scores 92.7% HumanEval and fits single B200.
1
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF trending on Hugging Face
GGUF quantized uncensored DeepSeek model trending at #30 on Hugging Face.
DeepSeek-V4.1-Flash-1017 Uncensored Model Trending on Hugging Face
AtomicChat releases 763B DeepSeek-V4.1-Flash-1017 uncensored GGUF quantized for single 12GB GPU with Strata.
1
AtomicChat publishes safety-ablated LFM3-1.7B GGUF
AtomicChat reports harmful-prompt refusals fell from 61.7% to 0% with MMLU unchanged at 41.0%.
ThinkBit preserves reasoning in scalar two-bit language models
On Qwen3-1.7B, a 0.52 GB recalibrated checkpoint scores 46.7 on MATH-500 versus 30.0 for EfficientQAT.
CCORE previews Qwen3.5-4B-3D-Coder, a 4B Three.js coding fine-tune
The independent early preview, trending #30, refreshed Q4_K_M and Q8_0; full weights and the dataset follow after October 28.
Some official Ollama low-bit GGUF tags fail code tasks despite intact weights
Seven of 305 official Ollama tags solved at most six of 164 HumanEval+ tasks.
LiquidAI publishes GGUF weights for LFM3-1.7B
The repo adds a QAD Q4_0 file meant to recover accuracy lost to Q4_0 quantization.
Unsloth publishes GGUF of NVIDIA Nemotron 3.5 Bolt E4B
The Q4_K_M build has 8B total parameters, 4B effective, and a 64K-token context.
DASLab releases GSQ-RCO GGUFs of DeepSeek-V4.1-Flash-1017
The IQ2_XXS build matches the base model’s reported task average, and every build is said to run on a 12 GB GPU with Strata.
Abliterated DeepSeek-V4.1-Flash GGUF trends on Hugging Face
The MIT-licensed text-generation upload has 156 likes and only 3 downloads; no evals or base-model changes are described.
Unsloth lists GGUF builds of Recursive's Flint coding model
Flint is a 39.8B MoE model with about 2.5B active parameters, scored by Recursive at 54.9% on Terminal-Bench 2.1.
XHToken releases Spark-X2.6-4B GGUF for on-device use
The 4B model keeps the Spark-X2.5 architecture and claims coding and agent gains from post-training alone.
Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console
A GitHub project ports llama.cpp to a jailbroken PlayStation 5 to run GGUF models natively.
What You Sign Is Not What You Run: The Verifiability Gap in Quantized LLM Supply Chains
Researchers find signed full-precision LLMs cannot verify popular GGUF builds, with verifiability at 0 of 198 repos.
LiquidAI/LFM2.5-24B-A2B-GGUF — new model trending #30 on Hugging Face
Liquid AI released GGUF weights for LFM2.5-24B-A2B, including a Q4_0 distillation build.
AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF — new model trending #30 on Hugging Face
AtomicChat published abliterated GGUF weights of the Qwen-Image 2.1 Turbo text encoder, sharply cutting chat refusals.
23
Meet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool Calling
Saluki 27B, a 7.89 GB 2-bit Qwen3.8-27B GGUF, beats the full model on tool calling.
unsloth/embeddinggemma-2-GGUF — new model trending #29 on Hugging Face
Unsloth released GGUF weights for Google DeepMind's EmbeddingGemma 2, a 740M multimodal embedding model.
2
openbmb/MiniCPM-V-4.7-35B-A3B-gguf — new model trending #30 on Hugging Face
OpenBMB released GGUF weights for MiniCPM-V 4.7 35B-A3B, an on-device multimodal MoE model.
Qwen3.8 27B addition in words
Simon Willison locally retests Qwen3.8 27B on summing numbers and answering in words.
SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF — new model trending #30 on Hugging Face
SC117 published abliterated GGUF quants of Qwen3.8-Flash-Next that swap 144 tensors while keeping GSQ-RCO scales.
Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia
Janus is a Go binary that runs GGUF models on AMD, Intel, and Nvidia GPUs via Vulkan.