Login
Integer Quantization: Deep Dive
(hello-fri-end.github.io) by matt_d | view | 1 comments
NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
(arxiv.org) by chrsw | view | 0 comments
Faiss vs. Turbovec vs. Infino: Comparing 4-bit vector quantization
(infino.ai) by ekechinwokah | view | 0 comments
Quantization for Neural Networks
(leimao.github.io) by eigenBasis | view | 0 comments
Ask HN: Does treating Inflation as a "Quantization Snap" resolve slow-roll?
by aplowe | view | 0 comments
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses
(quesma.com) by stared | view | 0 comments
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses
(quesma.com) by stared | view | 0 comments
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses
(quesma.com) by stared | view | 0 comments
How to run Qwen3.8-27B on a single 16GB card: quantizations and Llama.cpp flags
(autodidacts.io) by Curiositry | view | 0 comments
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses
(quesma.com) by stared | view | 0 comments
Quantization-Aware Healing:a compressed 4-bit model that outperf full-precision
(huggingface.co) by grigio | view | 0 comments
LLM Quantization Part 2: You're Gonna Need a Bigger VRAM
(lttlabs.com) by rldjbpin | view | 0 comments
LLM Quantization Part 2.5: Do Floats Dream of Real Numbers?
(lttlabs.com) by rldjbpin | view | 0 comments
LLM Quantization Part 3: Honey, I Shrunk the Numbers
(lttlabs.com) by rldjbpin | view | 0 comments
Compress and Forget: Bitsandbytes Quantization Amplifies Proactive Interference
(arxiv.org) by sbulaev | view | 0 comments
Hopf Spherical Compression and Quantization in C++23
(github.com) by rfgplk | view | 1 comments
Unsloth releases Dynamic v3 quantizations of Qwen3.8-27B
(huggingface.co) by Curiositry | view | 0 comments
GGUF Quantization Compared: Q4_K_M vs. IQ4_XS vs. IQ4_NL
(kaitchup.substack.com) by peter_d_sherman | view | 0 comments
DeepSeek V4 Pro at 207 tok/s with the full 1M context, no quantization
(runinfra.ai) by OsamaJaber | view | 0 comments
DeepSeek V4 Flash at 278 tok/s, full precision, no quantization
(runinfra.ai) by OsamaJaber | view | 0 comments
Muse Glimmer 30B unsloth GGUF format Q4, Q6, Q8 quantizations
(huggingface.co) by walrus01 | view | 0 comments
A Gentle Deep Dive into Quantization
(cuecloud.substack.com) by krav-sales | view | 0 comments
INT2 KV-cache quantization is getting surprisingly good
(arxiv.org) by yunuyean | view | 0 comments
A Visual Guide to Quantization – Demystifying the Compression of LLMs
(newsletter.maartengrootendorst.com) by sebg | view | 0 comments
Quantization hurts knowledge nonlinearly – Qwen3.6 27B case study
(quesma.com) by stared | view | 0 comments
Do Qwen 3.6 27B quantizations break the pelican?
(quesma.com) by stared | view | 0 comments
Show HN: Fast NF4 dequantization Triton kernel (1.41x faster than bitsandbytes
(github.com) by Griffith-7 | view | 0 comments
Scaling Law for Quantization-Aware Training
(arxiv.org) by JumpCrisscross | view | 0 comments
Negative squaring – pre-tilted 3-bit quantization beat naive 4-bit
(github.com) by faDOOM | view | 0 comments
Asymmetric Quantization: Near-Lossless Retrieval with 97% Storage Reduction
(mixedbread.com) by breadislove | view | 0 comments
LLM Quantization Project Part 1: What Even Is an LLM?
(lttlabs.com) by LabsLucas | view | 1 comments
Mlx-optiq: per-layer mixed-precision LLM quantization for Apple Silicon
(mlx-optiq.com) by codelion | view | 0 comments
GGUF vs. GPTQ vs. AWQ: The Plain-English Guide to LLM Quantization
(vettedconsumer.com) by ermantrout | view | 0 comments
GGUF vs. GPTQ vs. AWQ: The Plain-English Guide to LLM Quantization
(vettedconsumer.com) by ermantrout | view | 0 comments
KVarN: Native vLLM KV-cache quantization back end by Huawei
(github.com) by theanonymousone | view | 0 comments
Spikes in LLMs Are Bias Vectors: Spike-Free Quantization
(arxiv.org) by sbulaev | view | 0 comments
Show HN: Glq LLM quantization using E8 lattice
(github.com) by acd | view | 0 comments
Emergent Quantization from a Dynamic Vacuum
(journals.aps.org) by bookofjoe | view | 0 comments
3.125-Bit LLM quantization bypassing tensor cores
(blog.djellalmohamedaniss.workers.dev) by dmaniss | view | 0 comments
Evaluation of Various MLX Quantizations
(github.com) by d-_-b | view | 1 comments
Scalar and Binary Quantization for Pgvector Vector Search and Storage (2024)
(jkatz05.com) by eigenBasis | view | 0 comments
Emergent Quantization from a Dynamic Vacuum
(journals.aps.org) by davedx | view | 0 comments
Quantization for Modern AI Systems (70-page free eBook)
(pawankjha.substack.com) by pawanjha25 | view | 0 comments
Advanced Quantization Algorithm for LLMs
(github.com) by lastdong | view | 0 comments
LLM Quantization
(huggingface.co) by Anon84 | view | 0 comments
A DuckDB extension for vector search indexes with pluggable quantization
(github.com) by CheeseWang | view | 0 comments
The Quantization Robustness of Diffusion Language Models in Coding Benchmarks
(arxiv.org) by matt_d | view | 0 comments
SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
(arxiv.org) by matt_d | view | 0 comments
A guide to model quantization in fine-tuning (and how to pick the right GGUF)
(siquick.com) by siquick | view | 0 comments
Quantization, LoRA, and the 8% Problem Benchmarking Local LLMs for Production AI
(walsenburgtech.com) by cowartc | view | 0 comments