Açık kaynak radarı

Havuz

Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.

109

repo · sayfa 1 / 3

Sırala

Yıldız/gün (hız)Son gün (★/gün)Son hafta (★/gün)Son ay (★/gün)Toplam yıldız AI önem skoru Bana uyum Commit (28g)Yazar (28g)En yeni

Konu

Tümü AI / LLM18 Veri9 Geliştirici araçları13 Diğer3 SaaS altyapı13 Web11

Süz

Yalnız hareketli Yalnız analizli≥ 0 ≥ 100 ≥ 500 ≥ 2.000

Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.

EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster

Sırala:

Etiketler yükleniyor…

Aktif quantization

1
mw00/project-maya 2.393
Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU
88,6/gün ort. +44 son gün +83,6 son 18g 836 commit 19 yazar Cuda 06 Eki 2026 güncellendi dün
cuda deepseek deepseek-v4 glm glm-5 llm llm-inference local-llm
2.393
2
prabanta-dev/janas 566
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cp
13,2/gün ort. +10 son gün +17,9 son 30g 62 commit 1 yazar C 20 Eyl 2026 güncellendi 4 gün önce
avx2 c cpu-inference gguf inference-engine linux llm local-llm
566
3
FareedKhan-dev/kimi-k3-in-c önem 38gpt6-luna uyum 20gpt6-luna 9.274
kimi-k3-in-c, Kimi K3 modelinde inference çalıştırmayı hedefleyen bağımlılıksız bir C99 motorudur.
Neden yükseliyor · 57 günde 8.683 yıldız alması ve Kimi K3'ü 8 GB RAM'li CPU'da çalıştırma iddiası dikkat çekiyor; ancak son 28 gündeki 12 commit'in tek yazardan gelmesi, ilginin bağımsız teknik doğrulama veya geniş katkıcı tabanıyla desteklendiğini göstermiyor.
99,7/gün ort. +7 son gün +14,3 son 30g 0 commit 0 yazar C 01 Ağu 2026 güncellendi 02 Eki 2026
avx2 c99 cpu-inference deep-learning from-scratch inference-engine kimi-k3 linear-attention
9.274
4
Yamz-Labs/kyojin 225
Kyojin: open-source engine that runs the largest open models on one mini PC or one graphics card, about 2× faster than llama.cpp. AMD (ROCm)
7,3/gün ort. +0 son gün +7,2 son 28g 637 commit 5 yazar Python 02 Eki 2026 güncellendi dün
amd exl3 inference llm quantization rocm strix-halo
225
5
fermionresearch/phonon 324
Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images
4,9/gün ort. +2 son gün +6,8 son 30g 7 commit 1 yazar Python 28 Ağu 2026 güncellendi 6 gün önce
asr cuda docker low-bit mlx pytorch quantization speech-recognition
324
6
RyanCodrai/turbovec önem 53gpt6-luna uyum 68gpt6-luna 17.452
turbovec, TurboQuant ile vektörleri sıkıştırıp Rust ve Python üzerinden arama yapmayı sağlayan yerel bir vector index kütüphanesidir.
Neden yükseliyor · 185 günde 17.245 yıldız almış olması ve bellek tasarrufu ile hızlı yerel arama vaadi dikkat çekiyor. Ancak son 28 günde commit ve farklı yazar sayısı sıfır; bu veriler yükselişin güncel olarak sürdüğünü göstermiyor. README'deki performans karşılaştırmaları proje tarafından bildiriliyor, bağımsız doğrulama bilgisi verilen ölçümlerde yok.
79/gün ort. +2 son gün +6,1 son 30g 3 commit 1 yazar Rust 26 Mar 2026 güncellendi 27 gün önce
ann avx512 embeddings faiss nearest-neighbor neon python quantization
17.452
7
BoumedineBillal/esp32-pie-asr 48
Live English speech recognition on the ESP32-P4: a 65.7M-parameter streaming transducer in 2/4-bit weights, faster than real time, on the ch
6/gün ort. +6 son gün +4,3 son 4g 7 commit 1 yazar C++ 25 Eki 2026 güncellendi 2 gün önce
asr embedded esp32-p4 quantization risc-v simd speech-recognition tinyml
48
8
JakeATX/llamAmpere 208
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s
3,7/gün ort. +1 son gün +2,4 son 30g 806 commit 2 yazar C++ 07 Eyl 2026 güncellendi dün
ampere consumer-gpu cuda ggml gguf kv-cache-quantization llama-cpp llm
208
9
wanshuiyin/ARIS-in-AI-Offer 629
Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /rend
3,8/gün ort. +1 son gün +2,2 son 30g 4 commit 1 yazar Python 19 May 2026 güncellendi 4 gün önce
ai-interview aris cheatsheet chinese claude-code deep-learning diffusion flow-matching
629
10
ronitgupta138/Vectra-Core 64
⚡ In-Memory Vector Search Engine & HNSW ANN Graph in Java 21 Loom. Sub-millisecond KNN retrieval, 8-bit scalar quantization (SQ8), 16,000+ Q
2,2/gün ort. +0 son gün +2 son 25g 31 commit 1 yazar Java 04 Eki 2026 güncellendi 4 gün önce
ai-search ann approximate-nearest-neighbors concurrency embeddings high-throughput hnsw in-memory-database
64
11
IST-DASLab/GSQ 127
Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).
0,7/gün ort. +1 son gün +1,6 son 30g — commit Python 12 May 2026 güncellendi 11 Tem 2026
gguf llm post-training-quantization quantization
127
12
Dreamer-Toby/STEPQuant 102
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
3/gün ort. +0 son gün +1,6 son 30g 2 commit 1 yazar Python 29 Eyl 2026 güncellendi 11 gün önce
large-language-models llm post-training-quantization quantization
102
13
tlack/babytalk 54
Optimized ESP32-S3/P4 fully offline speech to text and text to speech system for Micropython and AtomVM, featuring a finetuned STT model for
1,5/gün ort. +0 son gün +1,3 son 23g — commit C 26 Eyl 2026 güncellendi 20 gün önce
asr atomvm edge-ai elixir erlang esp-idf esp32 esp32-p4
54
14
whitecircle/halo 839
Halo is an open-source framework built by White Circle for training large language and multimodal models
12,3/gün ort. +0 son gün +1 son 30g 9 commit 4 yazar Python 26 Ağu 2026 güncellendi 2 gün önce
agent async-rl distributed-training fine-tuning grpo large-language-models llm lora
839
15
Blackwellboy/model-serving-minefield 165
Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quant k
1,7/gün ort. +1 son gün +1 son 30g 34 commit 1 yazar Python 27 Tem 2026 güncellendi dün
benchmarking chat-template cuda debugging llama-cpp llm-serving lm-eval local-llm
165
16
0xBakeer/TandemLLM 70
An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine that d
2/gün ort. +0 son gün +1 son 16g — commit Python 28 Eyl 2026 güncellendi bugün
ai-agents dgx-spark exl3 inference-engine llm-inference local-ai nvfp4 quantization
70
17
Saganaki22/ComfyUI-Ming-3-tts 28
Native ComfyUI port of Ming-3.0-tts, supporting 0.5B and Tiny 9B speech generation.
2,2/gün ort. +1 son gün +0,9 son 12g — commit Python 20 Eki 2026 güncellendi 3 gün önce
comfyui ming ming-tts one-shot quantization text-to-speech tts voice-clone
28
18
zhangshuibai/molten 23
Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.
2,9/gün ort. +0 son gün +0,9 son 7g 7 commit 1 yazar Metal 25 Eki 2026 güncellendi 5 gün önce
apple-silicon gpu-kernels inference-engine inference-optimization lfm2 liquid-ai llama-cpp llm
23
19
omgitsbase/llmash 37
Ollama-compatible LLM server on a tuned llama.cpp fork. Beats vllm by 40% on single stream decode, and by 20% on multi stream decode, and be
0,6/gün ort. +0 son gün +0,8 son 30g — commit C++ 06 Eyl 2026 güncellendi dün
abliteration cuda gemma gguf inference-engine llama-cpp llm llm-inference
37
20
Magnvs7/Promethevs 30
PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-then-c
2,5/gün ort. +1 son gün +0,8 son 9g — commit 21 Eki 2026 güncellendi 11 gün önce
consumer-hardware deepseek deepseek-v4 llm llm-inference local-inference local-llm mixture-of-experts
30
21
Josia-doit/ComfyUI_JosiaNodes 41
一套功能完整、轻量稳定的 ComfyUI 实用节点集。初衷是为了平替一些断更插件的功能，会持续更新一些新开发的节点插件。有好的创意可以发Issues，我会力所能及想办法做出来。全中文界面，原生控件，不依赖第三方库。
0,2/gün ort. +0 son gün +0,7 son 30g — commit JavaScript 02 Nis 2026 güncellendi 5 gün önce
ai-image-generation ai-inference comfyui comfyui-custom-nodes comfyui-nodes flux generative-ai gguf
41
22
ExVRAM/exvram-lab 35
Compute-for-memory research lab for running larger LLMs on memory-constrained consumer GPUs. Official website exvram.pro
0,9/gün ort. +0 son gün +0,7 son 25g — commit Python 26 Eyl 2026 güncellendi 10 gün önce
benchmarking blackwell cuda gpu inference llm local-llm low-bit
35
23
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash 488
Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/a
2,6/gün ort. +0 son gün +0,6 son 30g 1 commit 1 yazar Python 25 Nis 2026 güncellendi 28 gün önce
abliteration blackwell dflash dgx-spark llm nvfp4 quantization qwen
488
24
LoopLegendHum/token-bench 21
Published: 2026-10-19
1,4/gün ort. +0 son gün +0,6 son 10g — commit C# 18 Eki 2026 güncellendi 15 gün önce
ai-tools benchmark charts csharp dotnet gpu-offload llama-cpp llm-performance
21
25
RobinOscillate/tensor-inspect 19
Published: 2026-10-19
1,3/gün ort. +0 son gün +0,6 son 10g — commit C# 18 Eki 2026 güncellendi 15 gün önce
ai-tools csharp diff dotnet dtype gguf layer-list llm
19
26
Joakimpalm-Zen/xyntetik-runner 30
Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b
0,3/gün ort. +0 son gün +0,5 son 30g — commit C 10 Tem 2026 güncellendi bugün
agents c constrained-decoding cuda edge-ai fine-tuning gguf inference
30
27
Fjordshupropagate/gguf-quant 19
Published: 2026-10-18
1,3/gün ort. +0 son gün +0,5 son 12g — commit C# 18 Eki 2026 güncellendi 16 gün önce
ai-tools csharp dotnet gguf llama-cpp llm local-ai mit-license
19
28
Tylogi/TyloQuant 94
Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the ha
0,9/gün ort. +0 son gün +0,4 son 30g — commit C++ 24 Tem 2026 güncellendi 4 gün önce
apple-silicon cuda deepseek gemma gguf llm llm-inference llm-quantization
94
29
asher/gmlx 46
Local inference platform for K/IQ-quant GGUF models on Apple Silicon
0,4/gün ort. +0 son gün +0,4 son 30g — commit Python 19 Tem 2026 güncellendi 3 gün önce
anthropic-api apple-silicon gguf gguf-model-support gguf-runner inference inference-engine llm
46
30
IST-DASLab/disaggregated-quantization 32
Disaggregated quantization official codebase
0,8/gün ort. +0 son gün +0,4 son 30g — commit Jupyter Notebook 21 Eyl 2026 güncellendi 13 gün önce
llm quantization quantization-aware-training vllm
32
31
lifeidle/qwen3.8-flash-next-5090-laptop-24gb-strata 26
Qwen3.8-Flash-Next 177B MoE (IQ3_S 3.44bpw) on RTX 5090 Laptop 24GB: full-model quality @ 97.7 tok/s · dual-lane 256K full-context unlocked
0,5/gün ort. +1 son gün +0,4 son 28g — commit Python 10 Eyl 2026 güncellendi 6 gün önce
256k-context flash-next gguf iq3-xxs local-llm moe mtp quantization
26
32
Lowaltitudeflight/local-llm-tuning-guide 19
A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decodi
1,1/gün ort. +0 son gün +0,4 son 15g — commit Python 16 Eki 2026 güncellendi dün
benchmarking decision-guide gpu-serving inference-optimization kv-cache llm llm-deployment llmops
19
33
FujitsuResearch/OneCompression 445
Python package for LLM compression
2,1/gün ort. +0 son gün +0,3 son 30g 19 commit 4 yazar Python 30 Mar 2026 güncellendi 6 gün önce
llm qep quantization vllm
445
34
hwdsl2/scribecrate 119
ScribeCrate: open-source, self-hosted Whisper speech-to-text server powered by faster-whisper. OpenAI-compatible transcription and English t
0,6/gün ort. +1 son gün +0,3 son 30g — commit Python 08 Nis 2026 güncellendi 3 gün önce
inference openai quantization speech-recognition speech-to-text whisper self-hosted ai
119
35
SamsungLabs/NanoQuant 26
[ICML 2026] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models
0,2/gün ort. +0 son gün +0,3 son 30g — commit Python 28 May 2026 güncellendi 03 Tem 2026
cuda icml-2026 llm post-training-quantization ptq pytorch quantization
26
36
IvenKooLab/minimax-h3-turing 23
MiniMax H3 video generation on 2080Ti 22G (Turing sm_75) - field-tested handbook, workflows & FAQ
0,4/gün ort. +1 son gün +0,3 son 29g — commit Python 01 Eyl 2026 güncellendi 4 gün önce
2080ti benchmark comfyui comfyui-nodes field-tested frame-interpolation lora low-vram
23
37
assassinaj602/sate_ai 18
Fault injection framework for on-device AI. Pure Dart core (sate_core) + Flutter package (sate_ai). Android, iOS, Web, and CLI targets.
0,2/gün ort. +0 son gün +0,3 son 17g — commit Dart 28 Tem 2026 güncellendi 14 gün önce
ai-reliability chaos-engineering dart developer-tools edge-ai edge-computing fault-injection flutter
18
38
huawei-csl/KVarN 513
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Cal
3,3/gün ort. +0 son gün +0,2 son 30g 0 commit 0 yazar Python 29 May 2026 güncellendi 22 Haz 2026
agentic-ai kv-cache long-context quantization vllm llm llm-inference
513
39
giannisanni/pulsar 231
SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs
2,1/gün ort. +1 son gün +0,2 son 30g 0 commit 0 yazar Rust 13 Tem 2026 güncellendi 01 Eyl 2026
cuda gguf glm inference-engine llm local-llm mixture-of-experts moe
231
40
timtoole02/Camelid 221
Camelid: a Rust-native local inference backend with evidence-gated model compatibility.
1,2/gün ort. +0 son gün +0,2 son 30g 86 commit 4 yazar Rust 01 May 2026 güncellendi 18 gün önce
apple-silicon gguf inference llama llm local-first metal openai-compatible
221
41
mattn/tensai 118
A tiny neural-network framework in pure Go with AVX2 SIMD kernels (GOEXPERIMENT=simd)
1,6/gün ort. +0 son gün +0,2 son 30g 11 commit 1 yazar Go 19 Ağu 2026 güncellendi 25 gün önce
autograd avx2 deep-learning gguf golang llm machine-learning neural-networks
118
42
Geekgineer/needle-rs 106
600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.
0,6/gün ort. +0 son gün +0,2 son 30g — commit Rust 17 May 2026 güncellendi 20 Eyl 2026
ai browser-ai function-calling llm no-std rust tool-calling transformer
106
43
tensormux/kernel-skills 87
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quant
0,4/gün ort. +0 son gün +0,2 son 30g — commit TypeScript 10 Nis 2026 güncellendi 21 Haz 2026
ai-coding cuda gpu-kernels high-performance-computing kernel-optimization llm-agents prompt-engineering quantization
87
44
rajveer43/VeloxQuant-MLX 33
Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods with Metal kernels
0,2/gün ort. +0 son gün +0,2 son 30g — commit Python 19 Nis 2026 güncellendi 2 gün önce
kv llm mlx quantization kv-cache macos ondeviceai apple-silicon
33
45
WestWaters/pollard-weights 33
A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from flas
0,4/gün ort. +1 son gün +0,2 son 30g — commit Python 07 Ağu 2026 güncellendi dün
diagnostics exl3 gguf gptq llama-cpp llm low-resource mac
33
46
shyringo/qwen3.8-27b-in-c 23
Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools;
0,3/gün ort. +0 son gün +0,2 son 30g — commit C 24 Ağu 2026 güncellendi 09 Eyl 2026
ai c cpu-inference generative-ai gguf inference inference-engine large-language-models
23
47
shyringo/qwen3.8-flash-next-in-c 23
The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no GP
0,4/gün ort. +0 son gün +0,2 son 30g — commit C 03 Eyl 2026 güncellendi 09 Eyl 2026
ai c cpu-inference generative-ai gguf inference inference-engine large-language-models
23
48
shashankswe2020-ux/rigspark 20
Which local LLMs can your computer run? Hardware-aware CLI, TUI and GUI: yes/slow/no verdicts and tok/s from your GPU VRAM and RAM, then ver
0,2/gün ort. +0 son gün +0,2 son 30g — commit Rust 04 Ağu 2026 güncellendi 3 gün önce
ai apple-silicon cli gpu hardware inference llama-cpp llm
20
49
quantumaikr/quant.cpp 405
LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.
1,8/gün ort. +0 son gün +0,1 son 30g 0 commit 0 yazar C 28 Mar 2026 güncellendi 26 Nis 2026
delta-compression embeddable gguf kv-cache llm llm-inference pure-c quantization
405
50
jjang-ai/jangq 232
JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon
1/gün ort. +0 son gün +0,1 son 30g 112 commit 1 yazar Python 15 Mar 2026 güncellendi dün
gguf llamacpp llm mlx mlxllm quantization apple-silicon jang-quantization
232