GGUFでのトークナイズ確認、これまで何となくで済ませていたけど、こうやって可視化できるとデバッグの解像度が段違いになるね。
デコードの不整合に悩んでる人は一度見ておくと良いかも。ローカルLLM開発者は必須の視点になりそう。
https://nowokay.hatenablog.com/entry/2026/03/26/153226
#AI #ローカルLLM #GGUF #エンジニア
0
0
0
0
Hashtag
#GGUF
Advertisement · 728 × 90
[JP] 【学習不要】特定の層を
[EN] No Learning Needed: Just
ai-minor.com/blog/en/2026-03-19-17739...
#LLM #GGUF #推論回路 #AI #Tech
0
0
0
0
#openSUSE just released Cavil-Qwen3.5-4B; an #opensource AI model that automates #legal compliance checks for #software licenses and copyright notices. Runs on modest hardware thanks to #GGUF #quantization. #AI #Linux news.opensuse.org/2026/03/16/o...
8
1
0
0
Unsloth Dynamic 2.0 pushes GGUF inference past 30 tokens/s on a single RTX 4090, yet its memory footprint still hampers true edge deployment. 🤖 #gguf
Unsloth Dynamic 2.0 GGUFs
0
0
0
0
🚀 Excited to announce LLMNoMaid!
A small but mighty custom LLM trained from a GPT-2 base, sprinkled with the intelligence of GPT-5, Claude Sonnet, Gemini 3, and Deepseek 3.x. (And other datasets too!)
#LLMNoMaid #AI #CustomLLM #GGUF
0
0
0
0
We’ve just released a new blog on GGUF 🚀
Learn what it is, why it matters, and how it’s shaping local AI models.
👉 arkdevlabs.com/global/blog/...
#AI #GGUF #MachineLearning #ArkDevLabs
0
0
0
0
New release!
Gemma-3-270M (GGUF) is now available for local AI workflows.
Grab it here 👇
huggingface.co/Open4bits/ge...
#LocalAI #GGUF #HuggingFace
1
0
0
0
New release!
Gemma-3-270M-IT (GGUF) is now live — great for Italian language tasks and local inference.
👉 huggingface.co/Open4bits/ge...
#LocalAI #GGUF #HuggingFace
1
0
0
0
We’ve just released a new blog on GGUF 🚀
Learn what it is, why it matters, and how it’s shaping local AI models.
👉 arkdevlabs.com/global/blog/...
#AI #GGUF #MachineLearning #ArkDevLabs
1
1
0
0
Fine-tuning Qwen-8B под проприетарный синтаксис (CADINP) на одной RTX 3090: опыт инженера-конструктора Возможно ли на одной ...
#LLM #fine-tuning #локальные #нейросети #RTX #3090 #Unsloth #Qwen #DeepSeek #GGUF #SOFiSTiK
Origin | Interest | Match
0
0
0
0
Lance o TempFS Um protótipo para orquestrar contêineres temporários para modelos GGUF usando Node.js e Podman.
O projeto foca em ambientes efêmeros e limpeza automática de recursos.
github.com/FabioSmuu/Te...
#AI
#GGUF
#LLM
#LlamaCPP
#NodeJS
#Podman
#Containers
#Ubuntu
#Sandboxing
#Automation
0
0
0
0
LLM 양자화 완벽 가이드! INT4로 메모리 87.5% 절감, FP8로 처리량 43% 향상. GPTQ vs AWQ vs GGUF 비교, Llama 3 양자화 성능 벤치마크, Q4까지 손실 2% 미만! Pruning + Knowledge Distillation 경량화 기법, 하드웨어별 추천 전략, QLoRA Fine-tuning까지!
#AWQ #FP8 #GGUF #GPTQ #INT4 #INT8 #KnowledgeDistillation #Llama3 #llamacpp
doyouknow.kr/618/llm-quan...
0
0
0
0
Because the runtime includes llama.cpp natively, you can load any #GGUF model (#Llama, #Mistral, #CodeLlama, etc.) with zero extra setup.
It’s literally import #llm and go.
0
0
1
0
You can build a full ChatGPT-style app that runs entirely offline with #Python + #JavaScript + a #GGUF model… all inside one executable.
No servers, no cloud APIs, no telemetry.
That’s the interesting part.
1
0
1
0
#OpenAI #OSS #Safeguard 🧠⚙️ Run local #LLM #guardrails with open-source models (120B & 20B). Works with #GGUF, #MLX & Safetensors. Run with @lmstudio-ai.bsky.social @ollamabot.bsky.social
🔗 Link in first 💬⤵️
📜 Apache 2.0 License
#AI #RAG Repost 🔁
1
0
1
0
A first Experience with LLaMA.CPP A first basic test putting my hands on LLaMA.CPP Introduction What is LLama.CPP llama.cpp is a highly optimized C/C++ library designed to run large language models...
#llamacpp #llm #huggingface #gguf
Origin | Interest | Match
0
0
0
0
Llama.cpp now pulls GGUF models directly from Docker Hub By using OCI-compliant registries like Docker Hub, the AI community can build more robust, reproducible, and scalable MLOps pipelines.
Learn more: docker.com/blog/llama.cpp-pulls-gguf-models-from-docker-hub/
#Docker #llamacpp #GGUF
3
1
0
0
🆕 mnya.tw/cc/word/2571...
#ComfyUI #QwenImage #Qwen_Image #12GB #VRAM #執行 #本地 #開源 #AI繪圖生成教學 #AI #生成教學 #生成 #GGUF #量化 #模型 #工作流 #軟體應用 #人工智慧 #AI插畫 #AI繪圖 #繪圖 #插畫
1
0
0
0
🆕 mnya.tw/cc/word/2557...
⭐️ 研究時間 6 小時，精華文章
#ComfyUI #QwenImageEdit #Qwen_Image_Edit #12GB #VRAM #執行 #本地 #開源 #AI圖片編輯工具 #AI #圖片編輯工具 #圖片編輯 #工具 #換裝 #改場景 #GGUF #量化 #模型 #工作流 #軟體應用 #多媒體 #人工智慧 #AI繪圖 #繪圖 #靜圖處理
1
0
0
0
Hat es schon jemand lokal zum Laufen gebracht?
#apertus #gguf
Ich möchte es mit #LMStudio benutzen, weil da schon ein #MCP-Server läuft mit #filesystem und #homeassistant
Alle Tips willkommen.
0
0
1
0
Run Large Language Models Locally: A Guide to Creating GGUF Files for CPU Inference Ever felt like you need a supercomputer to run a decent large language model (LLM)? Continue reading on Medium »
#ai #gguf #llm-large-language-model #machine-learning
Origin | Interest | Match
0
1
0
0
Русскоязычные LLM для вызова инструментов, переводов и финансовой аналитики 🧠 Русскоязычные LLM для вызова и...
#typescript #javascript #python #llm #ai #openai #grok #agents #tensorflow #gguf
Origin | Interest | Match
0
0
0
0
Русскоязычные LLM для вызова инструментов, переводов и финансовой аналитики Предыдущая статья с подборкой м...
#agents #AI #gguf #grok #javascript #llm #OpenAI #python #TensorFlow #TypeScript
Origin | Interest | Match
0
0
0
0
Ускорение DeepSeek-R1 с подвохом: Когда токены в секунду врут о реальной скорости Токены летят быстрее, а результ...
#deepseek #deepseek #r1 #deepseek #r1-0528 #ai #llm #llm-модели #gguf #кодогенерация #local
Origin | Interest | Match
0
0
0
0
🛠️ SOLAIRIA: Offline AI Assistant
SOLAIRIA is a customizable, offline alternative to ChatGPT, supporting GGUF models. It offers both GPU and CPU modes, ensuring compatibility across Windows and Linux systems.
#SOLAIRIA #OfflineAI #GGUF #PrivacyFirst
0
0
0
0
Microsoft Clippy Returns as AI Assistant, Empowered By LLMs You Can Run Locally on Your PC
#AI #Clippy #AIClippy #AIAssistants #LLMs #LocalAI #OpenSource #ElectronJS #LlamaCpp #GGUF #Gemma3 #Llama3 #Phi4 #Qwen3 #RetroTech #MicrosoftOffice #OnDeviceAI
winbuzzer.com/2025/05/06/m...
2
0
0
0
