GitHub‑OSS‑Trends

Heißeste Open-Source-Projekte der letzten 24 Stunden

public-apis/public-apis · ⭐ 486,892 freeCodeCamp/freeCodeCamp · ⭐ 456,935 EbookFoundation/free-programming-books · ⭐ 398,694 openclaw/openclaw · ⭐ 391,636 nilbuild/developer-roadmap · ⭐ 369,149 vinta/awesome-python · ⭐ 326,013 awesome-selfhosted/awesome-selfhosted · ⭐ 324,801 obra/superpowers · ⭐ 296,596 public-apis/public-apis · ⭐ 486,892 freeCodeCamp/freeCodeCamp · ⭐ 456,935 EbookFoundation/free-programming-books · ⭐ 398,694 openclaw/openclaw · ⭐ 391,636 nilbuild/developer-roadmap · ⭐ 369,149 vinta/awesome-python · ⭐ 326,013 awesome-selfhosted/awesome-selfhosted · ⭐ 324,801 obra/superpowers · ⭐ 296,596

Live source: HF Trending Snapshot source: GitHub grouped snapshot Estimated: Heat / VRAM

Angesagte Modelle

Δ 24 h

Die Standardreihenfolge entspricht der Hugging-Face-Trendliste (7-Tage-Likes).

Nur kommerziell nutzbare Lizenzen (z. B. Apache 2.0 / MIT) New listings only

JEV-27B-VL New

autotrust

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 21

See model card
clef New

Cloudflare

Δ 24 h +48%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 75

See model card
GEV-26B-Decide New Hot

autotrust

Δ 24 h +71%

Lizenz — Other LLM

VRAM

—

HF-Task

text-classification

HF

Model Card

Hippo Heat 100

See model card
embeddinggemma-2 New

google

Δ 24 h +52%

Lizenz — Other LLM

VRAM

—

HF-Task

feature-extraction

HF

Model Card

Hippo Heat 79

See model card
Kolibri-1 New

Aleph-Alpha

Δ 24 h +46%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 71

See model card
Qwen-Image-2.1-Uncensored-GGUF New

abenzerps

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

text-to-image

HF

Model Card

Hippo Heat 21

See model card
clef-flash New

Cloudflare

Δ 24 h +51%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 78

See model card
Xing4.0-29B-A4B-GGUF New

Venastine-Research

Δ 24 h +55%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 82

See model card
humanizer New

jialinyyzz

Δ 24 h +52%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 79

See model card
LTX-2.5 New

Lightricks

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-to-video

HF

Model Card

Hippo Heat 21

See model card
laya New

convaiinnovations

Δ 24 h +55%

Lizenz — Other LLM

VRAM

—

HF-Task

text-classification

HF

Model Card

Hippo Heat 82

See model card
Qwen3.8-27B New

Qwen

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 21

See model card
ema-lightning New

canberkkkkkk

Δ 24 h +48%

Lizenz — Other Audio

VRAM

—

HF-Task

text-to-speech

HF

Model Card

Hippo Heat 74

See model card
Qwen3.8-Flash-Next-GSQ-RCO-GGUF New

ISTA-DASLab

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 21

See model card
Qwen-Image-2.1 New

Qwen

Δ 24 h +61%

Lizenz — Other Vision

VRAM

—

HF-Task

text-to-image

HF

Model Card

Hippo Heat 89

See model card
GLM-5.3-UNCENSORED-EXL3-3.0bpw New

Infatoshi

Δ 24 h +40%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 62

See model card
ZDTaichu5.0-9B New

TaichuAI

Δ 24 h +49%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 76

See model card
BFS-Best-Face-Swap New

Alissonerdx

Δ 24 h +65%

Lizenz — Other Vision

VRAM

—

HF-Task

image-to-image

HF

Model Card

Hippo Heat 93

See model card
OrcaSAQ-2-Cyber-27B-Uncensored-GGUF New

orcarouter

Δ 24 h +52%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 79

See model card
embeddinggemma-2-GGUF New

unsloth

Δ 24 h +54%

Lizenz — Other LLM

VRAM

—

HF-Task

feature-extraction

HF

Model Card

Hippo Heat 81

See model card
Qwen3.8-Flash-Next New

Qwen

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 21

See model card
GLM5.3-Flash-E224-DGX-Spark New

autotrust

Δ 24 h +45%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 70

See model card
DeepSeek-V4.1-Flash New

deepseek-ai

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 21

See model card
Ternary-Bonsai-2-27B-gguf New

prism-ml

Δ 24 h +HF Hot

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 21

See model card
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF New

DavidAU

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 21

See model card
whistle New

Cactus-Compute

Δ 24 h +41%

Lizenz — Other Audio

VRAM

—

HF-Task

automatic-speech-recognition

HF

Model Card

Hippo Heat 64

See model card
Qwen3.8-27B-GSQ-RCO-GGUF New

ISTA-DASLab

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 21

See model card
GEV-26B-Decide-NVFP4 New

autotrust

Δ 24 h +52%

Lizenz — Other LLM

VRAM

—

HF-Task

text-classification

HF

Model Card

Hippo Heat 79

See model card
Qwen3.8-Flash-Next-Uncensored-GGUF New

orcarouter

Δ 24 h +68%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 97

See model card
d1-3B New

LiquidAI

Δ 24 h +45%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 70

See model card
Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF New Hot

SC117

Δ 24 h +69%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 98

See model card
MiniMax-H3 New

MiniMaxAI

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-video

HF

Model Card

Hippo Heat 21

See model card
Qwen-Image-2.1-viggle-turbo New

Viggle

Δ 24 h +66%

Lizenz — Other Vision

VRAM

—

HF-Task

text-to-image

HF

Model Card

Hippo Heat 94

See model card
Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF New

ISTA-DASLab

Δ 24 h +69%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 98

See model card
FrogNano-4B-2609 New

microsoft

Δ 24 h +36%

Lizenz — Other LLM

VRAM

—

HF-Task

—

HF

Model Card

Hippo Heat 56

See model card
Qwen3.8-27B-GGUF New

unsloth

Δ 24 h +HF Hot

Lizenz — Other LLM

VRAM

—

HF-Task

—

HF

Model Card

Hippo Heat 21

See model card
MiniMax-H3-360-Orbit-LoRA New

pablodawson

Δ 24 h +49%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-video

HF

Model Card

Hippo Heat 76

See model card
MiniMax-H3-Character-Swap-LoRA New

akatz-ai

Δ 24 h +53%

Lizenz — Other Vision

VRAM

—

HF-Task

video-to-video

HF

Model Card

Hippo Heat 80

See model card
Prism New

FrancisRing

Δ 24 h —

Lizenz — Other Vision

VRAM

—

HF-Task

image-to-video

HF

Model Card

Hippo Heat 0

See model card
Nemotron-3-Diarization New

nvidia

Δ 24 h +58%

Lizenz — Other LLM

VRAM

—

HF-Task

voice-activity-detection

HF

Model Card

Hippo Heat 86

See model card
Phonon-2 New

FermionResearch

Δ 24 h +43%

Lizenz — Other Audio

VRAM

—

HF-Task

automatic-speech-recognition

HF

Model Card

Hippo Heat 67

See model card
GLiNER2.5-Decide New

fastino

Δ 24 h +59%

Lizenz — Other LLM

VRAM

—

HF-Task

token-classification

HF

Model Card

Hippo Heat 87

See model card
sam3 New

facebook

Δ 24 h +HF Hot

Lizenz — Other LLM

VRAM

—

HF-Task

mask-generation

HF

Model Card

Hippo Heat 21

See model card
speaker-diarization-community-1 New

pyannote

Δ 24 h +HF Hot

Lizenz — Other Audio

VRAM

—

HF-Task

automatic-speech-recognition

HF

Model Card

Hippo Heat 21

See model card
Julia-1 New

SupersonicLabs

Δ 24 h +44%

Lizenz — Other LLM

VRAM

—

HF-Task

text-classification

HF

Model Card

Hippo Heat 68

See model card
Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF New Hot

ukisai

Δ 24 h +70%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 99

See model card
CLM-v0.1-8B New

Contrastive-LM

Δ 24 h +43%

Lizenz — Other LLM

VRAM

—

HF-Task

text-ranking

HF

Model Card

Hippo Heat 67

See model card
JEV-9B New

autotrust

Δ 24 h +66%

Lizenz — Other LLM

VRAM

—

HF-Task

text-classification

HF

Model Card

Hippo Heat 94

See model card
LTX-2.5-22b-IC-LoRA-Alpha-Gen New

Lightricks

Δ 24 h +46%

Lizenz — Other Vision

VRAM

—

HF-Task

video-to-video

HF

Model Card

Hippo Heat 71

See model card
pplx-decider-v1-27b New

perplexity-ai

Δ 24 h +40%

Lizenz — Other LLM

VRAM

—

HF-Task

text-classification

HF

Model Card

Hippo Heat 62

See model card

Gruppierter Repository-Vergleich

Jeder Abschnitt listet Repos derselben Klasse (z. B. Agent: OpenClaw, NanoBot, PicoClaw). Die Spaltenbedeutungen sind in allen Gruppen gleich. „Commits (30 T.)“ folgt dem rollierenden Fenster des Scrapers.

Snapshot: 08.10.2026

Datenquellen und Methodik

Public formula (within each group): Score = 100 × [0.30·Stars + 0.15·Forks + 0.30·Commits30d + 0.15·Contributors + 0.05·(1-Issues) + 0.05·(1-PRs)], after per-group min-max normalization.

Agent

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues
1	openclaw/openclaw	88,5	391.636	82.292	16.091	3.513	9.531
2	NousResearch/hermes-agent	67,6	252.120	54.328	17.583	4.371	47.648
3	affaan-m/ECC	29,3	275.231	41.058	345	398	364
4	deepseek-ai/deepseek-harness	28,9	245.676	29.443	4.245	55	0
5	langchain-ai/langchain	22	147.579	24.734	221	3.743	630
6	Significant-Gravitas/AutoGPT	21,6	187.699	45.937	525	863	648
7	firecrawl/firecrawl	11,7	189.682	10.049	252	175	531
8	langflow-ai/langflow	8,2	155.587	10.190	171	389	1.144
9	DietrichGebert/ponytail	7,2	158.133	8.491	91	111	20
10	farion1231/cc-switch	6,1	141.413	9.462	359	263	2.957

Multi-Agent

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues
1	lobehub/lobehub	68,8	83.058	15.957	868	359	1.047
2	TauricResearch/TradingAgents	55,4	110.228	21.197	192	24	94
3	zhayujie/CowAgent	53,2	47.274	10.375	1.017	183	55
4	danny-avila/LibreChat	45,4	45.403	9.323	637	419	853
5	FoundationAgents/MetaGPT	29,1	70.777	8.998	0	148	142
6	openai/openai-agents-python	27,7	29.908	4.853	240	407	8
7	Yeachan-Heo/oh-my-claudecode	23,9	39.679	3.551	328	167	8
8	agentscope-ai/agentscope	13,8	32.898	3.614	170	159	561
9	wshobson/agents	13,1	40.296	4.289	35	88	6
10	OpenBMB/ChatDev	7	34.463	4.320	0	19	82

Inferenz

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues
1	ggml-org/llama.cpp	66	130.674	24.186	646	2.096	2.482
2	BerriAI/litellm	62,5	60.357	12.137	5.914	1.782	5.340
3	earendil-works/pi	43,7	113.430	14.415	514	300	308
4	sgl-project/sglang	34,8	36.869	9.377	1.661	2.020	5.546
5	microsoft/onnxruntime	17,4	22.037	4.285	372	1.013	1.755
6	k2-fsa/sherpa-onnx	7,7	15.165	1.753	28	247	658
7	GeeeekExplorer/nano-vllm	7,2	15.741	2.666	0	15	99
8	abetlen/llama-cpp-python	5,9	10.637	1.464	4	196	687
9	h2oai/h2ogpt	5,6	11.949	1.296	0	78	328
10	CVHub520/X-AnyLabeling	5,4	10.619	1.175	20	58	6

LLM-Bibliothek

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues
1	huggingface/transformers	64,8	167.053	34.768	334	4.157	2.358
2	unslothai/unsloth	45,7	77.463	7.144	2.100	400	839
3	fighting41love/funNLP	21,4	83.755	15.288	0	13	54
4	router-for-me/CLIProxyAPI	18,2	54.476	8.291	507	269	657
5	asgeirtj/system_prompts_leaks	17,3	69.122	11.234	82	26	58
6	sickn33/antigravity-awesome-skills	15,9	47.355	6.894	380	395	4
7	langfuse/langfuse	14,7	35.518	3.951	776	219	1.025
8	labmlai/annotated_deep_learning_paper_implementations	13,7	67.535	6.755	0	42	44
9	ComposioHQ/awesome-claude-skills	13,4	76.698	8.986	0	29	1.659
10	huggingface/pytorch-image-models	8	37.202	5.214	96	214	42

Trainings-Framework

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues
1	pytorch/pytorch	67,2	103.889	31.612	2.104	7.139	17.704
2	vllm-project/vllm	50,1	93.387	23.126	1.687	3.685	8.597
3	AUTOMATIC1111/stable-diffusion-webui	45,4	165.216	32.601	0	638	2.510
4	Comfy-Org/ComfyUI	32,1	136.601	16.212	205	355	5.091
5	tensorflow/models	27,2	77.655	44.788	8	963	1.272
6	rasbt/LLMs-from-scratch	21,7	106.214	16.339	12	73	3
7	keras-team/keras	16,5	64.354	19.802	150	1.577	244
8	ultralytics/ultralytics	13	62.302	11.835	339	469	78
9	ultralytics/yolov5	9,2	58.115	17.459	4	350	24
10	CorentinJ/Real-Time-Voice-Cloning	5,5	60.173	9.379	0	20	177

Serving

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues
1	open-webui/open-webui	73,4	154.212	22.540	225	881	288
2	PDFMathTranslate/PDFMathTranslate	40	37.390	3.341	688	59	168
3	janhq/jan	33,3	44.852	3.074	490	184	542
4	Mintplex-Labs/anything-llm	28,7	66.820	7.456	145	263	330
5	chatchat-space/Langchain-Chatchat	15,1	38.675	6.256	0	173	32
6	AlexsJones/llmfit	14,4	37.708	2.420	66	154	80
7	1Panel-dev/1Panel	13,8	37.126	3.372	80	133	367
8	lm-sys/FastChat	10,6	39.549	4.775	0	246	1.044
9	Zackriya-Solutions/meetily	7,9	31.532	3.442	17	20	364
10	lss233/kirara-ai	5,5	19.068	1.832	0	49	3

Evaluation

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues
1	confident-ai/deepeval	64,4	18.702	2.032	124	337	708
2	bitnami/charts	50,5	10.417	10.307	8	2.780	12
3	prometheus-community/helm-charts	48,2	6.214	5.394	89	1.815	153
4	helmfile/helmfile	20,2	5.215	369	40	405	24
5	open-compass/opencompass	13,5	7.496	879	7	186	412
6	komodorio/helm-dashboard	11,2	5.779	364	6	58	18
7	stackrox/kube-linter	8,8	3.523	278	16	99	90
8	omerbsezer/Fast-Kubernetes	7,4	3.855	1.433	0	5	4
9	helm/chartmuseum	5,5	3.846	411	0	88	120
10	roboll/helmfile	3,9	4.033	551	0	224	525

RAG / Vektorsuche

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues
1	milvus-io/milvus	76,5	46.341	4.282	178	385	1.430
2	qdrant/qdrant	65,9	34.976	2.733	218	209	752
3	langchain4j/langchain4j	46,1	13.216	2.595	142	509	943
4	chroma-core/chroma	35,3	29.465	2.552	38	196	916
5	simdjson/simdjson	33	24.381	1.307	52	203	76
6	Tencent/APIJSON	25,4	18.398	2.274	39	98	235
7	datawhalechina/all-in-rag	23,3	11.813	5.844	3	12	28
8	gka/chroma.js	9	10.598	551	6	45	66
9	svcvit/Awesome-Dify-Workflow	8,7	10.782	1.089	0	2	26
10	std-microblock/chromatic	5	8.478	400	0	1	4

Snapshot-Daten, kein Live-GitHub-Stream. Updates laufen per geplanter REST/GraphQL-Erfassung, JSON-Schreiben und Rebuild.

GitHub‑zentrierte Signale

Repositories, Stars, Forks, Issues/PRs, Release‑Takt und Topics; Aggregation nach Organisation, Sprache oder Themen.

Projekte auf GitHub Explore ansehen

Kernmetriken

Star‑Velocity, Commit‑Frequenz, Issue/PR‑Aktivität, Beitragsverteilung, Release‑Rhythmus—mit Tages/Wochen/Monats‑Fenstern für Zeitreihen oder Heatmaps.

Ingestion und Aktualisierung

GitHub REST/GraphQL, öffentliche Datensätze oder Aggregatoren wie RSSHub; Actions zum periodischen Abruf und Normalisieren, Schreiben nach JSON oder D1, dann statische Seiten oder Read‑only‑Edge‑APIs.

Typen und Domänen

LLM / Inferenz‑Stack (Serving, Kernel, Quantisierung etc.)
Agenten, Multi‑Agenten, Tool‑Nutzung und Orchestrierung
Evals, Benchmarks, Datensätze und reproduzierbare Leaderboards
Training, Fine‑Tuning, Alignment und Engineering‑Toolchains
Lokales Deployment, Inferenz‑Services, Edge/Endpoint
Daten, RAG, Retrieval und Vector‑Store‑Ökosysteme

Häufige Fehldeutungen

Stars mit Modellqualität gleichsetzen—Hype kann vom Benchmark abweichen.
Nur kurze Zeitfenster—Spitzen können Kampagnen sein; längere Commit-Kurven tragen mehr Signal.
Issues/PRs ignorieren—gesunde Projekte zeigen oft dichte Wartung jenseits der Stars.
Persönliche und Organisations-Repos mischen—Governance und Release-Takt können stark abweichen.
GitHub als gesamtes Ökosystem sehen—wichtige Arbeit kann proprietär oder woanders gehostet sein.

Wöchentlicher KI-Branchenüberblick

Stand 8. Oktober 2026 umfasst diese Hugging-Face-Hotlist 50 Einträge. Nach 24-Stunden-Wachstum fallen „GEV-26B-Decide“, „Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF“, „Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF“, „Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF“, „Qwen3.8-Flash-Next-Uncensored-GGUF“ auf. Häufig oben vertretene Organisationen: autotrust, Qwen, Cloudflare, google—ein Hinweis auf schnelle Releases, Forks und Pipeline-Updates.

Etwa 50 Zeile(n) sind in diesem Snapshot als neu gelistet markiert—oft neue Gewichte, Quantisierungen oder Pipeline-Tags.

Tokens / Hosting: Hacker News hebt „Show HN: LLM Fuzz CI“ hervor; Hacker News hebt „AHM Statement on OpenAI's October 6 Release of Mathematical Documents“ hervor; Hacker News hebt „Dear LLM, or how I stopped getting generic advice“ hervor. Hinweise zu Preisen, Regionen und Rollout-Tempo für gehostete Inferenz.

Der gruppierte GitHub-Vergleich umfasst 8 Ökosystem-Segmente, um Modell-Hype mit Engineering-Aktivität (Stars, Commits, Issues/PRs) zu vergleichen.

Zur Startseite

Angesagte Modelle

JEV-27B-VL New

clef 🚀 New

GEV-26B-Decide 🚀 New Hot

embeddinggemma-2 🚀 New

Kolibri-1 🚀 New

Qwen-Image-2.1-Uncensored-GGUF New

clef-flash 🚀 New

Xing4.0-29B-A4B-GGUF 🚀 New

humanizer 🚀 New

LTX-2.5 New

laya 🚀 New

Qwen3.8-27B New

ema-lightning 🚀 New

Qwen3.8-Flash-Next-GSQ-RCO-GGUF New

Qwen-Image-2.1 🚀 New

GLM-5.3-UNCENSORED-EXL3-3.0bpw 🚀 New

ZDTaichu5.0-9B 🚀 New

BFS-Best-Face-Swap 🚀 New

OrcaSAQ-2-Cyber-27B-Uncensored-GGUF 🚀 New

embeddinggemma-2-GGUF 🚀 New

Qwen3.8-Flash-Next New

GLM5.3-Flash-E224-DGX-Spark 🚀 New

DeepSeek-V4.1-Flash New

Ternary-Bonsai-2-27B-gguf New

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF New

whistle 🚀 New

Qwen3.8-27B-GSQ-RCO-GGUF New

GEV-26B-Decide-NVFP4 🚀 New

Qwen3.8-Flash-Next-Uncensored-GGUF 🚀 New

d1-3B 🚀 New

Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF 🚀 New Hot

MiniMax-H3 New

Qwen-Image-2.1-viggle-turbo 🚀 New

Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF 🚀 New

FrogNano-4B-2609 🚀 New

Qwen3.8-27B-GGUF New

MiniMax-H3-360-Orbit-LoRA 🚀 New

MiniMax-H3-Character-Swap-LoRA 🚀 New

Prism New

Nemotron-3-Diarization 🚀 New

Phonon-2 🚀 New

GLiNER2.5-Decide 🚀 New

sam3 New

speaker-diarization-community-1 New

Julia-1 🚀 New

Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF 🚀 New Hot

CLM-v0.1-8B 🚀 New

JEV-9B 🚀 New

LTX-2.5-22b-IC-LoRA-Alpha-Gen 🚀 New

pplx-decider-v1-27b 🚀 New

Gruppierter Repository-Vergleich

Agent

Multi-Agent

Inferenz

LLM-Bibliothek

Trainings-Framework

Serving

Evaluation

RAG / Vektorsuche

GitHub

GitHub‑zentrierte Signale

Kernmetriken

Ingestion und Aktualisierung

Typen und Domänen

Häufige Fehldeutungen

Weiterlesen

Wöchentlicher KI-Branchenüberblick

clef New

GEV-26B-Decide New Hot

embeddinggemma-2 New

Kolibri-1 New

clef-flash New

Xing4.0-29B-A4B-GGUF New

humanizer New

laya New

ema-lightning New

Qwen-Image-2.1 New

GLM-5.3-UNCENSORED-EXL3-3.0bpw New

ZDTaichu5.0-9B New

BFS-Best-Face-Swap New

OrcaSAQ-2-Cyber-27B-Uncensored-GGUF New

embeddinggemma-2-GGUF New

GLM5.3-Flash-E224-DGX-Spark New

whistle New

GEV-26B-Decide-NVFP4 New

Qwen3.8-Flash-Next-Uncensored-GGUF New

d1-3B New

Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF New Hot

Qwen-Image-2.1-viggle-turbo New

Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF New

FrogNano-4B-2609 New

MiniMax-H3-360-Orbit-LoRA New

MiniMax-H3-Character-Swap-LoRA New

Nemotron-3-Diarization New

Phonon-2 New

GLiNER2.5-Decide New

Julia-1 New

Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF New Hot

CLM-v0.1-8B New

JEV-9B New

LTX-2.5-22b-IC-LoRA-Alpha-Gen New

pplx-decider-v1-27b New