All tags
Catalogue tag

#quantization

Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.

47 records
Tagged “quantization”Ranked by health index
PyPI
67Goodhealth index
google-ai-edge/LiteRT-CLI
A convenient CLI to streamline LiteRT related development workflows, including converting, quantizing, compiling, managing, running, benchmarking and visualizing LiteRT (TFLite) models on various hardwares (CPU / GPU / NPU) across platforms (desktop, mobile or cloud).
Python★ 41↓ 80/moSep 8, 2026
Apache-2.0Sep 8, 2026 · metrics 2.10.0
PyPI
67Goodhealth index
pjordanandrsn/grouped-nf4-gemm
Triton kernels for 4-bit MoE inference: grouped NF4/MXFP4 GEMM, INT4 GEMV, FP8 paged attention, and CPU/NVMe expert streaming.
Python★ 2↓ 3,717/moSep 24, 2026
MITSep 24, 2026 · metrics 2.10.0
PyPI
65Goodhealth index
SYSTRAN/faster-whisper
Faster Whisper transcription with CTranslate2
Python★ 25.4K↓ 8.7M/moSep 16, 2026
MITSep 16, 2026 · metrics 2.10.0
PyPI
65Goodhealth index
asher/gmlx
Local inference platform for K/IQ-quant GGUF models on Apple Silicon
Python★ 31↓ 2,075/moSep 25, 2026
Custom licenseSep 25, 2026 · metrics 2.10.0
PyPI
63Moderatehealth index
jagmarques/nexusquant
Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated.
Python★ 25Jul 16, 2026
Custom licenseJul 16, 2026 · metrics 2.10.0
PyPI
62Moderatehealth index
RobTand/gridbook
Out-of-tree vLLM plugin and open format spec for NVFP4-CB / FP8-CB product-codebook weights — 2-6 bit-per-weight LLM quantization served on native Blackwell tensor cores.
Python · Cuda★ 12↓ 1,474/moSep 18, 2026
Apache-2.0Sep 18, 2026 · metrics 2.10.0
PyPI
60Moderatehealth index
manunicholasjacob/llama-roofline
Is your llama.cpp decode memory-bandwidth-bound? Find out in one command.
Python★ 1↓ 12.4K/moOct 13, 2026
MITOct 13, 2026 · metrics 2.10.0
PyPI
59Moderatehealth index
jjang-ai/jangq
JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon
Python · Swift★ 225↓ 1,557/moSep 13, 2026
No licenseSep 13, 2026 · metrics 2.10.0
npm
54Moderatehealth index
mkbabb/value.js
CSS value units for color, length, angles, & c.
TypeScript★ 0↓ 156/moSep 12, 2026
MITSep 12, 2026 · metrics 2.10.0
PyPI · npm · crates.io
53Moderatehealth index
JunHwan-Kwon/deepbom
Local static analysis and evidence generation for deployed AI model artifacts
JavaScript · Rust★ 2↓ 3,094/moSep 4, 2026
Apache-2.0Sep 4, 2026 · metrics 2.10.0
crates.io
42Weakhealth index
RecursiveIntell/turbo-quant
Experimental Rust vector-compression sidecars implementing TurboQuant (ICLR 2026), PolarQuant and QJL research primitives, with exact reranking and workload-scoped benchmark receipts.
Rust · Python★ 26↓ 2,127/moOct 20, 2026
MITOct 20, 2026 · metrics 2.10.0
npm
42Weakhealth index
stfurkan/bitgpu
Fast WebGPU runtime for 1-bit (binary-weight) LLMs in the browser. Bit-exact, zero runtime dependencies.
TypeScript · WGSL · Python★ 27↓ 204/moSep 14, 2026
MITSep 14, 2026 · metrics 2.10.0
PyPI
38Weakhealth index
fermionresearch/phonon
Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images
Python★ 258Oct 20, 2026
Apache-2.0Oct 20, 2026 · metrics 2.10.0
PyPI
22At Riskhealth index
nactttch/g2n
A torch.compile backend that pays attention: custom FX fusion passes, a Triton LayerNorm kernel, and a persistent compile cache. Apache-2.0 free core of the g2n platform.
Python★ 0↓ 2,377/moSep 15, 2026
Apache-2.0Sep 15, 2026 · metrics 2.10.0
PyPI
19Criticalhealth index
blue-oil/blueoil
Bring Deep Learning to small devices
Python · C++★ 247Sep 11, 2026
Apache-2.0Sep 11, 2026 · metrics 2.10.0