Açık kaynak radarı

Havuz

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

104

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

AI / LLM

Tümü ai-agents 5.678 llm 4.854 mcp 4.358 claude 2.807 anthropic 1.255 openai 966 rag 866 agents 799 prompt-engineering 785 image-generation 558 knowledge-graph 381 generative-ai 364 text-to-speech 300 semantic-search 214 speech-recognition 173 embeddings 154 vector-search 138 llmops 108

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
leonxger/deepseek-colab 53
Uncensored DeepSeek-V4.1-Flash IQ2_XS on Google Colab
7,6/gün ort. +2 son gün 1 commit 1 yazar Python 30 Eki 2026 güncellendi 7 gün önce
colab cuda deepseek deepseek-v4 gguf google-colab gpu llama-cpp
53
2
synchopate/llama-modchip 73
🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs).
9,1/gün ort. +1 son gün 41 commit 1 yazar Python 29 Eki 2026 güncellendi dün
avx512 cpu-inference hpc llama-cpp mamba2 mixture-of-experts nemotron speculative-decoding
73
3
BoumedineBillal/esp32-pie-asr 55
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
4,6/gün ort. +1 son gün 7 commit 1 yazar C++ 25 Eki 2026 güncellendi 5 gün önce
asr embedded esp32-p4 quantization risc-v simd speech-recognition tinyml
55
4
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.
1,9/gün ort. +0 son gün — commit Metal 25 Eki 2026 güncellendi 8 gün önce
apple-silicon gpu-kernels inference-engine inference-optimization lfm2 liquid-ai llama-cpp llm
23
5
alleyxd/quantpicker 9
Measures which GGUF quant of a model to run on your GPU: real speed and quality loss (KL divergence), not estimates.
0,6/gün ort. -6 son gün — commit Rust 23 Eki 2026 güncellendi 9 gün önce
benchmark gguf llama-cpp llm local-llm quantization rust
9
6
Magnvs7/Promethevs 108
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
6,8/gün ort. +3 son gün 12 commit 1 yazar 21 Eki 2026 güncellendi 14 gün önce
deepseek llm local-inference mixture-of-experts quantization consumer-hardware deepseek-v4 llm-inference
108
7
Nhahan/Xevn 13
A 4B decision model built for Korean.
0,8/gün ort. +0 son gün — commit 21 Eki 2026 güncellendi 14 gün önce
calibration decision-model jev korean llm mlx quantization qwen
13
8
Saganaki22/ComfyUI-Ming-3-tts 28
Native ComfyUI port of Ming-3.0-tts, supporting 0.5B and Tiny 9B speech generation.
1,6/gün ort. +0 son gün — commit Python 20 Eki 2026 güncellendi 6 gün önce
comfyui ming one-shot quantization text-to-speech tts voice-clone voice-cloning
28
9
BobClawblaw/deepseek-v41-flash-mlx-m5-ultra 14
DeepSeek-V4.1-Flash-1017 on one 256 GB M5 Ultra: 1M context, 70.7-104.9 tok/s decode with DSpark drafts, 1,739-1,867 tok/s cold prompts (8k-
0,8/gün ort. +0 son gün — commit Python 19 Eki 2026 güncellendi 14 gün önce
apple-silicon deepseek deepseek-v4 llm llm-inference long-context m5-ultra metal
14
10
RobinOscillate/tensor-inspect 5
Published: 2026-10-19
0,3/gün ort. +0 son gün — commit C# 18 Eki 2026 güncellendi 18 gün önce
ai-tools csharp diff dotnet dtype gguf layer-list llm
5
11
Fjordshupropagate/gguf-quant 3
Published: 2026-10-18
0,2/gün ort. +0 son gün — commit C# 18 Eki 2026 güncellendi 19 gün önce
ai-tools csharp dotnet gguf llama-cpp llm local-ai mit-license
3
12
Lowaltitudeflight/local-llm-tuning-guide 42
A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decodi
2/gün ort. +13 son gün — commit Python 16 Eki 2026 güncellendi 2 gün önce
benchmarking decision-guide gpu-serving inference-optimization kv-cache llm llm-deployment llmops
42
13
mw00/project-maya 2.569
Run GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and
82,9/gün ort. +43 son gün 927 commit 15 yazar Cuda 06 Eki 2026 güncellendi bugün
cuda glm glm-5 llm llm-inference local-llm mixture-of-experts moe
2.569
14
The-SEMQ-Group/semq 13
Deterministic symbolic codes for embedding vectors. Byte-identical across CPUs and languages, content-addressed, diffable and verifiable. C
0,4/gün ort. +0 son gün — commit Python 05 Eki 2026 güncellendi 4 gün önce
audit c determinism embeddings machine-learning python quantization rag
13
15
ronitgupta138/Vectra-Core 65
⚡ 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/gün ort. +1 son gün 34 commit 1 yazar Java 04 Eki 2026 güncellendi dün
approximate-nearest-neighbors embeddings high-throughput hnsw java-21 machine-learning quantization similarity-search
65
16
Yamz-Labs/kyojin 230
Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, NVID
6,6/gün ort. +1 son gün 564 commit 3 yazar Python 02 Eki 2026 güncellendi bugün
amd exl3 inference llm quantization rocm strix-halo apple-silicon
230
17
lokutor-ai/oido önem 53gpt6-luna uyum 46gpt6-luna 130
Oído, ESP32-S3 üzerinde cloud veya NPU olmadan open-vocabulary speech recognition çalıştırmayı hedefleyen C tabanlı bir ASR motorudur.
Neden yükseliyor · Düşük maliyetli bir mikrodenetleyicide open-vocabulary ASR çalıştırma iddiası ve README’de verilen LibriSpeech sonuçları dikkat çekiyor. Repo 1 günlük ve 46 yıldız almış olsa da son 28 gündeki 6 commit’in tek yazardan gelmesi, ilginin henüz bağımsız benimseme veya sürdürülebilir geliştirme kanıtı olmadığını gösteriyor.
3,5/gün ort. +0 son gün 13 commit 3 yazar C 30 Eyl 2026 güncellendi dün
asr conformer edge-ai embedded esp-idf esp32 esp32-s3 microcontroller
130
18
Dreamer-Toby/STEPQuant 102
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
2,7/gün ort. +1 son gün 2 commit 1 yazar Python 29 Eyl 2026 güncellendi 14 gün önce
large-language-models llm post-training-quantization quantization
102
19
0xBakeer/TandemLLM 74
An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine that d
1,9/gün ort. +0 son gün — commit Python 28 Eyl 2026 güncellendi bugün
dgx-spark llm-inference nvfp4 qwen speculative-decoding ai-agents exl3 inference-engine
74
20
tlack/babytalk 55
Optimized ESP32-S3/P4 fully offline speech to text and text to speech system for Micropython and AtomVM, featuring a finetuned STT model for
1,3/gün ort. +0 son gün — commit C 26 Eyl 2026 güncellendi 3 gün önce
asr atomvm edge-ai elixir erlang esp-idf esp32 esp32-p4
55
21
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 — commit Python 26 Eyl 2026 güncellendi 13 gün önce
benchmarking blackwell cuda gpu inference llm local-llm low-bit
35
22
IST-DASLab/disaggregated-quantization 33
Disaggregated quantization official codebase
0,7/gün ort. +0 son gün — commit Jupyter Notebook 21 Eyl 2026 güncellendi 16 gün önce
llm quantization quantization-aware-training vllm
33
23
mark2008chen-sudo/qwen-image2.1-uncensored-comfyui 13
ComfyUI deployment kit for Qwen-Image-2.1 Uncensored (GGUF): ready-to-use t2i & image-edit workflows, ComfyUI-GGUF architecture patches, and
0,3/gün ort. +0 son gün — commit Python 21 Eyl 2026 güncellendi 21 Eyl 2026
comfyui comfyui-workflow gguf image-editing quantization qwen-image text-to-image uncensored
13
24
prabanta-dev/janas 635
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
13,5/gün ort. +18 son gün 58 commit 1 yazar C 20 Eyl 2026 güncellendi 2 gün önce
avx2 c cpu-inference gguf inference-engine linux llm local-llm
635
25
harshitkhandelwal208/hk 24
Local LLMs that run lean, load instantly and keep getting smarter. A from-scratch runtime + model format in Zig: zero-copy mmap, CPU/CUDA/Vu
0,4/gün ort. +0 son gün — commit Zig 13 Eyl 2026 güncellendi 15 gün önce
ai cuda gguf huggingface inference llm mmap model-container
24
26
JakeATX/llamAmpere 223
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. +2 son gün 638 commit 2 yazar C++ 07 Eyl 2026 güncellendi dün
ampere consumer-gpu cuda ggml gguf kv-cache-quantization llama-cpp llm
223
27
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 — commit C++ 06 Eyl 2026 güncellendi 3 gün önce
abliteration cuda gemma gguf inference-engine llama-cpp llm llm-inference
37
28
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 — commit C 03 Eyl 2026 güncellendi 09 Eyl 2026
ai c cpu-inference generative-ai gguf inference inference-engine large-language-models
23
29
alesha-pro/atlas 74
Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels for e
1,1/gün ort. -1 son gün — commit TypeScript 30 Ağu 2026 güncellendi 02 Eyl 2026
dataviz interpretability llm quantization visualization
74
30
Scorp1o117/FIT-GGUF 24
Fit-to-Size Intelligent Tensor Quantization for GGUF - deterministic, size-exact mixed quantization on llama.cpp presets. Turn any byte budg
0,4/gün ort. +0 son gün — commit Python 30 Ağu 2026 güncellendi 15 gün önce
ggml gguf llama-cpp llm model-compression quantization
24
31
vcruz305/GLM-5.3-Flash-EXL3-K2-DGX-Spark-recipe 26
vLLM recipe: GLM-5.3-Flash EXL3 K2 on one DGX Spark GB10. Native MTP k=2. Measured tok/s.
0,4/gün ort. +0 son gün — commit Python 29 Ağu 2026 güncellendi 10 Eyl 2026
dgx-spark exl3 glm llm quantization vllm
26
32
fermionresearch/phonon 331
Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images
4,7/gün ort. +3 son gün 5 commit 1 yazar Python 28 Ağu 2026 güncellendi 9 gün önce
asr cuda docker low-bit mlx pytorch quantization speech-recognition
331
33
ayutaz/sanoTTS-jp 70
559 K パラメータの日本語 TTS を ESP32-S3 で実時間合成。漢字かな交じり文の形態素解析・アクセント推定まで端末内で走る（M5Stack CoreS3 実機で確認）。推論は依存ゼロの C99、ブラウザ demo あり。arXiv:2608.21378 sanoTT
1/gün ort. +0 son gün — commit Python 27 Ağu 2026 güncellendi 4 gün önce
embedded esp32 esp32-s3 g2p japanese japanese-tts knowledge-distillation m5stack
70
34
peonist-ai/crucible 13
MoE expert compression toolkit — prune, merge, and forge specialist models for local inference.
0,2/gün ort. +0 son gün — commit Python 27 Ağu 2026 güncellendi 3 gün önce
expert-pruning gguf llama-cpp llm llm-inference local-llm machine-learning mixture-of-experts
13
35
whitecircle/halo 845
Halo is an open-source framework built by White Circle for training large language and multimodal models
11,7/gün ort. +2 son gün 6 commit 2 yazar Python 26 Ağu 2026 güncellendi bugün
agent async-rl distributed-training fine-tuning grpo large-language-models llm lora
845
36
siris9476/pulsarforge 23
0,3/gün ort. +0 son gün — commit C 25 Ağu 2026 güncellendi 10 Eyl 2026
avx2 c11 cpu-inference cpu-only disk-streaming gguf inference llama-cpp
23
37
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 — commit C 24 Ağu 2026 güncellendi 09 Eyl 2026
ai c cpu-inference generative-ai gguf inference inference-engine large-language-models
23
38
sauravsingla/MemVanta 41
Low-memory C++20 LLM inference runtime for quantized GGUF models on CPU — mmap-backed weights, paged KV cache, Q4/Q8 kernels, and reproducib
0,5/gün ort. +1 son gün — commit C++ 20 Ağu 2026 güncellendi 5 gün önce
benchmarking cpp cpp20 cpu-inference edge-ai gguf inference kv-cache
41
39
mattn/tensai 118
A tiny neural-network framework in pure Go with AVX2 SIMD kernels (GOEXPERIMENT=simd)
1,5/gün ort. +0 son gün — commit Go 19 Ağu 2026 güncellendi bugün
autograd avx2 deep-learning gguf golang llm machine-learning neural-networks
118
40
amasu/dgx-spark-qwen38 13
Docker compose configs for serving Qwen3.8-27B on a DGX Spark (GB10): vLLM+MTP current, SGLang+DSPARK + FP8 rollback stacks
0,2/gün ort. +0 son gün — commit Shell 18 Ağu 2026 güncellendi 10 gün önce
blackwell dgx-spark docker docker-compose fp8 gb10 llm llm-serving
13
41
chilly23/RP2040-and-ESP32-AI 53
Run a 28.9M-parameter TinyLM on ESP32-S3 with an RP2040 OLED display node for fully local embedded AI inference.
0,7/gün ort. +0 son gün — commit Python 17 Ağu 2026 güncellendi 17 Ağu 2026
arduino c claude-code codex cpp edge-ai embedded-ai embedded-systems
53
42
shyringo/deepseek-v4-flash-0731-in-c 28
Run the native 284B-A13B DeepSeek-V4-Flash-0731 LLM locally on one laptop CPU: pure C, 8 GB RAM minimum, no GPU, best TPOT 0.892 s/token, re
0,3/gün ort. +0 son gün — commit C 16 Ağu 2026 güncellendi 09 Eyl 2026
ai c cpu-inference deepseek deepseek-v4 generative-ai inference inference-engine
28
43
Greninja9257/LabLLM 39
A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from
0,5/gün ort. +0 son gün — commit Swift 15 Ağu 2026 güncellendi 20 Ağu 2026
ai apple-silicon artificial-intelligence deep-learning fine-tuning generative-ai gpt large-language-model
39
44
rostamlabs/rostam 36
Open-source vector database and sub-microsecond key-value store in one Go engine — embed it as a library, run it standalone, or replicate it
0,4/gün ort. +0 son gün — commit Go 10 Ağu 2026 güncellendi 27 Eyl 2026
bm25 database distributed-systems embeddings golang hnsw hybrid-search key-value-store
36
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. +0 son gün — commit Python 07 Ağu 2026 güncellendi 2 gün önce
diagnostics exl3 gguf gptq llama-cpp llm low-resource mac
33
46
rayl15/Godwit 25
Run GPT-OSS-120B on a 16 GB Mac. Streams mixture-of-experts weights from SSD so only the 2 GiB trunk stays resident. Swift + Metal, no depen
0,3/gün ort. +0 son gün — commit Swift 04 Ağu 2026 güncellendi 07 Ağu 2026
apple-silicon gpt-oss inference llm local-llm macos metal mixture-of-experts
25
47
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 — commit Rust 04 Ağu 2026 güncellendi bugün
ai apple-silicon cli gpu hardware inference llama-cpp llm
20
48
Bellman281/esp32-tinyLLM 48
Rust inference engine for a 28.9M-parameter PLE TinyLM on the ESP32-S3 — 9.4 tok/s, faster than the C implementation it was ported from
0,5/gün ort. +0 son gün — commit Rust 02 Ağu 2026 güncellendi 20 Ağu 2026
embedded esp32 esp32-s3 inference-engine llm quantization rust rust-crate
48
49
FareedKhan-dev/kimi-k3-in-c önem 38gpt6-luna uyum 20gpt6-luna 10.767
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.
111/gün ort. +396 son gün 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
10.767
50
200lz/omiv-kimi-k3-validation 11
Evidence-backed structural validation of Kimi K3 UD-IQ1_M and UD-Q4_K_XL split GGUF releases using OMIV.
0,1/gün ort. +0 son gün — commit Shell 30 Tem 2026 güncellendi 30 Tem 2026
ai-infrastructure gguf kimi-k3 llama-cpp llm model-integrity model-validation moe
11