GitHub‑OSS‑Trends

Heißeste Open-Source-Projekte der letzten 24 Stunden

codecrafters-io/build-your-own-x · ⭐ 523,994 sindresorhus/awesome · ⭐ 483,616 freeCodeCamp/freeCodeCamp · ⭐ 451,490 public-apis/public-apis · ⭐ 448,541 EbookFoundation/free-programming-books · ⭐ 391,586 openclaw/openclaw · ⭐ 382,477 nilbuild/developer-roadmap · ⭐ 360,187 vinta/awesome-python · ⭐ 307,358 codecrafters-io/build-your-own-x · ⭐ 523,994 sindresorhus/awesome · ⭐ 483,616 freeCodeCamp/freeCodeCamp · ⭐ 451,490 public-apis/public-apis · ⭐ 448,541 EbookFoundation/free-programming-books · ⭐ 391,586 openclaw/openclaw · ⭐ 382,477 nilbuild/developer-roadmap · ⭐ 360,187 vinta/awesome-python · ⭐ 307,358

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

Hy3 New

tencent

Δ 24 h +46%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 71

See model card
Qwythos-9B-Claude-Mythos-5-1M-GGUF New

empero-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
GLM-5.2 New

zai-org

Δ 24 h +67%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 96

See model card
Agents-A1 New

InternScience

Δ 24 h +53%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 80

See model card
Unlimited-OCR New

baidu

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 21

See model card
ThinkingCap-Qwen3.6-27B New

bottlecapai

Δ 24 h +43%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 67

See model card
tabfm-1.0.0-pytorch New

google

Δ 24 h +51%

Lizenz — Other LLM

VRAM

—

HF-Task

tabular-classification

HF

Model Card

Hippo Heat 78

See model card
fable-traces New

AliesTaha

Δ 24 h +44%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 68

See model card
Qwen-Fixed-Chat-Templates New

froggeric

Δ 24 h —

Lizenz — Other LLM

VRAM

—

HF-Task

—

HF

Model Card

Hippo Heat 0

See model card
Leanstral-1.5-119B-A6B New

mistralai

Δ 24 h +30%

Lizenz — Other LLM

VRAM

—

HF-Task

—

HF

Model Card

Hippo Heat 47

See model card
LongCat-2.0 New

meituan-longcat

Δ 24 h +37%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 58

See model card
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

HauhauCS

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 21

See model card
krea2-identity-edit New

conradlocke

Δ 24 h —

Lizenz — Other LLM

VRAM

—

HF-Task

—

HF

Model Card

Hippo Heat 0

See model card
Ornith-1.0-35B-GGUF New

deepreinforce-ai

Δ 24 h +HF Hot

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 21

See model card
gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF New

yuxinlu1

Δ 24 h +68%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 97

See model card
MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF New

GnLOLot

Δ 24 h +47%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 73

See model card
Giga-World-1 New

open-gigaai

Δ 24 h —

Lizenz — Other LLM

VRAM

—

HF-Task

—

HF

Model Card

Hippo Heat 0

See model card
DeepSeek-V4-Flash-GGUF New

unsloth

Δ 24 h +54%

Lizenz — Other LLM

VRAM

—

HF-Task

—

HF

Model Card

Hippo Heat 81

See model card
DeepSeek-V4-Pro-DSpark New

deepseek-ai

Δ 24 h +54%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 81

See model card
LocateAnything-3B New

nvidia

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Forks

299

GitHub

Quell-Repo

Hippo Heat 64

GitHub Stars · letzte 7 Tage

See model card
Qwen3.6-27B-NVFP4 New Hot

nvidia

Δ 24 h +71%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 100

See model card
NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 New

nvidia

Δ 24 h +52%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 79

See model card
Qwythos-9B-Claude-Mythos-5-1M New

empero-ai

Δ 24 h +63%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 91

See model card
Nemotron-Labs-Audex-30B-A3B New

nvidia

Δ 24 h +33%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 51

See model card
MOSS-Transcribe-Diarize New

OpenMOSS-Team

Δ 24 h +45%

Lizenz — Other Audio

VRAM

—

HF-Task

audio-text-to-text

HF

Model Card

Hippo Heat 70

See model card
Krea-2-Turbo New

krea

Δ 24 h +63%

Lizenz — Other Vision

VRAM

—

HF-Task

text-to-image

HF

Model Card

Hippo Heat 91

See model card
Qwen3.6-27B-MTP-GGUF New

unsloth

Δ 24 h +HF Hot

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 21

See model card
Krea-2-depth-controlnet New

Patil

Δ 24 h —

Lizenz — Other Vision

VRAM

—

HF-Task

image-to-image

HF

Model Card

Hippo Heat 0

See model card
Supra-Router-51M New

SupraLabs

Δ 24 h +37%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 57

See model card
Sun-Direction-Lora-Flux2Klein9B New

eric-venti-seeds

Δ 24 h —

Lizenz — Other Vision

VRAM

—

HF-Task

image-to-image

HF

Model Card

Hippo Heat 0

See model card
LTX-Best-Face-ID New

Alissonerdx

Δ 24 h —

Lizenz — Other Vision

VRAM

—

HF-Task

text-to-video

HF

Model Card

Hippo Heat 0

See model card
gemma-4-12B-coder-fable5-composer2.5-v1-GGUF New Hot

yuxinlu1

Δ 24 h +70%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 99

See model card
lingbot-video-moe-30b-a3b New

robbyant

Δ 24 h +30%

Lizenz — Other LLM

VRAM

—

HF-Task

—

HF

Model Card

Hippo Heat 47

See model card
cohere-transcribe-arabic-07-2026 New

CohereLabs

Δ 24 h +45%

Lizenz — Other Audio

VRAM

—

HF-Task

automatic-speech-recognition

HF

Model Card

Hippo Heat 70

See model card
gepard-1.0 New

nineninesix

Δ 24 h +39%

Lizenz — Other Audio

VRAM

—

HF-Task

text-to-speech

HF

Model Card

Hippo Heat 61

See model card
Tess-4-27B New

migtissera

Δ 24 h +33%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 51

See model card
Agents-A1-Q4_K_M-GGUF New

InternScience

Δ 24 h +55%

Lizenz — Other LLM

VRAM

—

HF-Task

—

HF

Model Card

Hippo Heat 82

See model card
jacobian-lens New

neuronpedia

Δ 24 h —

Lizenz — Other LLM

VRAM

—

HF-Task

—

HF

Model Card

Hippo Heat 0

See model card
ThinkingCap-Qwen3.6-27B-GGUF New

bottlecapai

Δ 24 h +66%

Lizenz — Other Vision

VRAM

—

HF-Task

image-text-to-text

HF

Model Card

Hippo Heat 94

See model card
MiniCPM5-1B New

openbmb

Δ 24 h +67%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 96

See model card
Ornith-1.0-9B-GGUF New

deepreinforce-ai

Δ 24 h +HF Hot

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 21

See model card
Qwen3.6-27B 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
Ornith-1.0-9B New

deepreinforce-ai

Δ 24 h +67%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 96

See model card
GigaChat3.5-432B-A28B New

ai-sage

Δ 24 h +36%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 56

See model card
Ornith-1.0-35B New Hot

deepreinforce-ai

Δ 24 h +70%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 99

See model card
krea2_turbo_style_reference New

ostris

Δ 24 h +38%

Lizenz — Other Vision

VRAM

—

HF-Task

text-to-image

HF

Model Card

Hippo Heat 59

See model card
Kokoro-82M New

hexgrad

Δ 24 h +HF Hot

Lizenz — Other Audio

VRAM

—

HF-Task

text-to-speech

HF

Model Card

Hippo Heat 21

See model card
Hy3-FP8 New

tencent

Δ 24 h +47%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 73

See model card
Nemotron-Labs-Audex-2B New

nvidia

Δ 24 h +36%

Lizenz — Other LLM

VRAM

—

HF-Task

text-generation

HF

Model Card

Hippo Heat 56

See model card
FLUX.1-dev New

black-forest-labs

Δ 24 h +70%

Lizenz — Other Vision

VRAM

—

HF-Task

text-to-image

HF

Model Card

Hippo Heat 99

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: 10.07.2026

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	Open PRs
1	openclaw/openclaw	95,3	382.477	80.274	7.576	2.849	6.352	2
2	NousResearch/hermes-agent	45,8	212.602	39.209	3.842	1.928	27.488	5
3	langchain-ai/langchain	32,5	141.471	23.506	266	3.698	415	61
4	affaan-m/ECC	29,9	228.167	34.993	184	289	88	64
5	Significant-Gravitas/AutoGPT	28,4	185.450	46.115	82	829	480	195
6	firecrawl/firecrawl	13,6	148.745	8.506	258	162	396	350
7	Shubhamsaboo/awesome-llm-apps	13,2	117.358	17.440	48	86	5	5
8	google-gemini/gemini-cli	12,2	105.888	14.230	47	688	1.372	205
9	langflow-ai/langflow	11,5	151.551	9.640	97	358	980	755
10	farion1231/cc-switch	8,6	115.600	7.733	194	192	1.850	474

Multi-Agent

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues	Open PRs
1	lobehub/lobehub	80,3	79.706	15.581	874	338	605	399
2	TauricResearch/TradingAgents	52,6	92.171	17.810	47	20	282	141
3	FoundationAgents/MetaGPT	38	69.293	8.836	0	148	138	113
4	zhayujie/CowAgent	36,1	45.906	10.260	170	134	25	4
5	danny-avila/LibreChat	35,4	40.538	8.325	205	376	567	258
6	openai/openai-agents-python	25,1	27.789	4.290	93	299	65	38
7	Yeachan-Heo/oh-my-claudecode	23,1	37.639	3.396	102	133	4	2
8	wshobson/agents	20,2	37.752	4.047	65	76	0	0
9	OpenBMB/ChatDev	13,1	33.699	4.197	2	19	67	23
10	agentscope-ai/agentscope	12,2	27.725	3.166	73	77	254	51

Inferenz

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues	Open PRs
1	ggml-org/llama.cpp	76,8	119.894	20.415	373	1.801	1.832	1
2	sgl-project/sglang	58,6	30.155	7.068	1.241	1.618	4.111	3
3	BerriAI/litellm	55,9	53.202	9.642	802	1.539	3.861	2
4	earendil-works/pi	43,5	69.420	8.523	400	235	60	8
5	microsoft/onnxruntime	21,2	21.054	4.046	197	947	1.420	619
6	k2-fsa/sherpa-onnx	12,9	13.486	1.542	38	215	598	48
7	GeeeekExplorer/nano-vllm	11,8	14.433	2.308	0	15	78	48
8	abetlen/llama-cpp-python	11	10.471	1.427	21	194	675	79
9	h2oai/h2ogpt	10,6	11.975	1.304	0	78	329	37
10	niedev/RTranslator	10	10.232	939	0	12	26	1

LLM-Bibliothek

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues	Open PRs
1	huggingface/transformers	79,5	162.447	33.858	280	4.020	2.477	1
2	unslothai/unsloth	46,5	67.990	6.121	569	243	1.049	254
3	langfuse/langfuse	36,9	30.880	3.251	581	187	699	398
4	sickn33/antigravity-awesome-skills	31,9	42.786	6.800	319	285	2	2
5	router-for-me/CLIProxyAPI	27,5	39.765	6.547	287	208	251	198
6	fighting41love/funNLP	27,3	81.726	15.251	0	13	52	8
7	asgeirtj/system_prompts_leaks	21,2	55.661	9.181	55	22	37	27
8	labmlai/annotated_deep_learning_paper_implementations	20	67.067	6.729	0	42	32	4
9	ComposioHQ/awesome-claude-skills	13,6	67.378	7.564	0	29	962	839
10	huggingface/pytorch-image-models	13,4	36.969	5.169	12	196	62	18

Trainings-Framework

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues	Open PRs
1	pytorch/pytorch	70,4	101.713	28.463	1.389	6.709	18.303	2
2	vllm-project/vllm	52,7	85.905	19.233	1.179	2.992	5.652	3
3	AUTOMATIC1111/stable-diffusion-webui	48,6	164.162	30.529	0	638	2.498	78
4	tensorflow/models	29,7	77.671	44.983	3	958	1.290	207
5	Comfy-Org/ComfyUI	27,5	120.194	14.119	154	326	4.258	379
6	rasbt/LLMs-from-scratch	24,1	98.865	15.174	0	66	4	1
7	keras-team/keras	19,2	64.186	19.752	43	1.529	231	98
8	ultralytics/ultralytics	15,6	59.322	11.351	249	389	198	138
9	ultralytics/yolov5	14,5	57.659	17.487	17	349	31	1
10	CorentinJ/Real-Time-Voice-Cloning	10,5	60.006	9.395	0	20	172	9

Serving

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues	Open PRs
1	open-webui/open-webui	93,1	144.951	20.982	390	851	389	154
2	Mintplex-Labs/anything-llm	37	63.053	6.895	147	213	325	25
3	AlexsJones/llmfit	29,5	29.266	1.786	217	78	52	19
4	1Panel-dev/1Panel	22,6	36.160	3.242	92	123	277	11
5	janhq/jan	22,5	43.481	2.895	91	178	383	73
6	chatchat-space/Langchain-Chatchat	20,4	38.280	6.219	0	173	22	16
7	PDFMathTranslate/PDFMathTranslate	14,5	35.513	3.171	0	57	139	21
8	lm-sys/FastChat	11,8	39.489	4.787	0	246	1.026	142
9	lss233/kirara-ai	10,7	18.846	1.833	0	48	3	0
10	Zackriya-Solutions/meetily	7,3	22.510	2.364	0	12	270	84

Evaluation

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues	Open PRs
1	confident-ai/deepeval	65,6	16.753	1.638	158	319	338	129
2	bitnami/charts	58,1	10.391	10.356	13	2.767	6	2
3	prometheus-community/helm-charts	43,8	6.156	5.376	89	1.787	227	111
4	helmfile/helmfile	24,8	5.154	353	50	388	30	14
5	open-compass/opencompass	20,3	7.184	802	39	175	424	83
6	komodorio/helm-dashboard	16,6	5.731	361	7	56	21	3
7	stackrox/kube-linter	13,4	3.478	267	21	94	86	9
8	omerbsezer/Fast-Kubernetes	11,6	3.540	1.268	0	5	4	3
9	helm/chartmuseum	9,7	3.832	407	1	88	116	25
10	roboll/helmfile	7,5	4.035	552	0	223	527	11

RAG / Vektorsuche

Rank	Repository	Score	Stars	Forks	Commits (30 T.)	Mitwirkende	Open issues	Open PRs
1	milvus-io/milvus	87,3	45.171	4.113	252	362	1.005	242
2	langchain4j/langchain4j	52,5	12.574	2.363	198	444	791	204
3	chroma-core/chroma	41,4	28.754	2.375	85	188	732	411
4	qdrant/qdrant	38,1	33.127	2.481	0	173	630	173
5	simdjson/simdjson	31,8	23.947	1.263	5	184	133	11
6	Tencent/APIJSON	27,5	18.392	2.274	7	93	244	3
7	datawhalechina/all-in-rag	26,1	9.401	4.686	0	11	17	4
8	svcvit/Awesome-Dify-Workflow	14,1	10.666	1.073	0	2	23	5
9	gka/chroma.js	13,3	10.572	549	0	43	71	10
10	std-microblock/chromatic	10	8.331	393	0	1	0	0

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 10. Juli 2026 umfasst diese Hugging-Face-Hotlist 50 Einträge. Nach 24-Stunden-Wachstum fallen „Qwen3.6-27B-NVFP4“, „gemma-4-12B-coder-fable5-composer2.5-v1-GGUF“, „Ornith-1.0-35B“, „FLUX.1-dev“, „gemma-4-12B-agentic-fable5-composer2.5-v2-3.…“ auf. Häufig oben vertretene Organisationen: nvidia, empero-ai, tencent, zai-org—ein Hinweis auf schnelle Releases, Forks und Pipeline-Updates.

Etwa 49 Zeile(n) sind in diesem Snapshot als neu gelistet markiert—oft neue Gewichte, Quantisierungen oder Pipeline-Tags.

Tokens / Hosting: Hacker News hebt „Mythos 5 offered outside the US by Anthropic“ hervor; Hacker News hebt „OpenAI and Google sell AI models to blacklisted China groups“ hervor; Hacker News hebt „Anthropic found a hidden space where Claude puzzles over concepts“ 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

Hy3 🚀 New

Qwythos-9B-Claude-Mythos-5-1M-GGUF New

GLM-5.2 🚀 New

Agents-A1 🚀 New

Unlimited-OCR New

ThinkingCap-Qwen3.6-27B 🚀 New

tabfm-1.0.0-pytorch 🚀 New

fable-traces 🚀 New

Qwen-Fixed-Chat-Templates New

Leanstral-1.5-119B-A6B 🚀 New

LongCat-2.0 🚀 New

Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

krea2-identity-edit New

Ornith-1.0-35B-GGUF New

gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF 🚀 New

MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF 🚀 New

Giga-World-1 New

DeepSeek-V4-Flash-GGUF 🚀 New

DeepSeek-V4-Pro-DSpark 🚀 New

LocateAnything-3B New

Qwen3.6-27B-NVFP4 🚀 New Hot

NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 🚀 New

Qwythos-9B-Claude-Mythos-5-1M 🚀 New

Nemotron-Labs-Audex-30B-A3B 🚀 New

MOSS-Transcribe-Diarize 🚀 New

Krea-2-Turbo 🚀 New

Qwen3.6-27B-MTP-GGUF New

Krea-2-depth-controlnet New

Supra-Router-51M 🚀 New

Sun-Direction-Lora-Flux2Klein9B New

LTX-Best-Face-ID New

gemma-4-12B-coder-fable5-composer2.5-v1-GGUF 🚀 New Hot

lingbot-video-moe-30b-a3b 🚀 New

cohere-transcribe-arabic-07-2026 🚀 New

gepard-1.0 🚀 New

Tess-4-27B 🚀 New

Agents-A1-Q4_K_M-GGUF 🚀 New

jacobian-lens New

ThinkingCap-Qwen3.6-27B-GGUF 🚀 New

MiniCPM5-1B 🚀 New

Ornith-1.0-9B-GGUF New

Qwen3.6-27B New

Ornith-1.0-9B 🚀 New

GigaChat3.5-432B-A28B 🚀 New

Ornith-1.0-35B 🚀 New Hot

krea2_turbo_style_reference 🚀 New

Kokoro-82M New

Hy3-FP8 🚀 New

Nemotron-Labs-Audex-2B 🚀 New

FLUX.1-dev 🚀 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

Hy3 New

GLM-5.2 New

Agents-A1 New

ThinkingCap-Qwen3.6-27B New

tabfm-1.0.0-pytorch New

fable-traces New

Leanstral-1.5-119B-A6B New

LongCat-2.0 New

gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF New

MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF New

DeepSeek-V4-Flash-GGUF New

DeepSeek-V4-Pro-DSpark New

Qwen3.6-27B-NVFP4 New Hot

NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4 New

Qwythos-9B-Claude-Mythos-5-1M New

Nemotron-Labs-Audex-30B-A3B New

MOSS-Transcribe-Diarize New

Krea-2-Turbo New

Supra-Router-51M New

gemma-4-12B-coder-fable5-composer2.5-v1-GGUF New Hot

lingbot-video-moe-30b-a3b New

cohere-transcribe-arabic-07-2026 New

gepard-1.0 New

Tess-4-27B New

Agents-A1-Q4_K_M-GGUF New

ThinkingCap-Qwen3.6-27B-GGUF New

MiniCPM5-1B New

Ornith-1.0-9B New

GigaChat3.5-432B-A28B New

Ornith-1.0-35B New Hot

krea2_turbo_style_reference New

Hy3-FP8 New

Nemotron-Labs-Audex-2B New

FLUX.1-dev New