Open models to add in one click

Collected from Hugging Face, GitHub and npm: open LLMs in GGUF, speech models like Whisper, embedding models. Every card links to its source, repeats the license and the numbers, and adds a short summary. One button adds it to LogiShell; without the app it leads to the install and brings you back.

Qwen3.8-2B-Distill-GGUF

model · LLM · by empero-ai

GGUF quantizations of empero-ai/Qwen3.8-2B — a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-2B architecture, the smallest member of the family — for llama.cpp, Ollama, LM Studio,…

apache-2.01.2 GB~2 GB RAMsource alive

622K downloads · 158 likes · numbers as of 2026-10-02
GLM-5.3-GGUF

model · LLM · by unsloth

See Unsloth Dynamic 3.0 GGUFs for our quantization benchmarks.

other45 GB~53 GB RAMsource alive

577K downloads · 97 likes · numbers as of 2026-10-02
parakeet-tdt-0.6b-v3-gguf

model · Speech · by handy-computer

parakeet-tdt-0.6b-v3: transcribe.cpp GGUF

cc-by-4.0463 MB~2 GB RAMsource alive

576K downloads · 6 likes · numbers as of 2026-10-02
parakeet-tdt-0.6b-v3

model · Speech · by nvidia

🦜 parakeet-tdt-0.6b-v3: Multilingual Speech-to-Text Model

cc-by-4.0681 MB~2 GB RAMsource alive

569K downloads · 1.2K likes · numbers as of 2026-10-02
JiRackDeltaNet_27b

model · LLM · by CMSManhattan

Qwen 3.8 27b migrated to Ternary Architedure - Benefits high quality CPU inference TQ2 on Llama.cpp and Ollama via QAT - Robotcs, Routing, Coding, Multimedia, Advanced tool calling via JiRackDeltaNet…

mit16 GB~19 GB RAMsource alive

554K downloads · 3 likes · numbers as of 2026-10-02
whisper-medium-gguf

model · Speech · by handy-computer

GGUF conversions of openai/whisper-medium for use with transcribe.cpp.

apache-2.0481 MB~2 GB RAMsource alive

546K downloads · 0 likes · numbers as of 2026-10-02
LFM2.5-230M-GGUF

model · LLM · by LiquidAI

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

other146 MB~1 GB RAMsource alive

535K downloads · 110 likes · numbers as of 2026-10-02
Qwen3.8-27B-DFlash2-GGUF

model · LLM · by z-lab

This repository contains GGUF conversions of incoai/Qwen3.8-27B-DFlash2, the DFlash 2 draft model for Qwen/Qwen3.8-27B. It is not a standalone language model: it runs inside a speculative decoding se…

apache-2.01.1 GB~2 GB RAMsource alive

520K downloads · 146 likes · numbers as of 2026-10-02
LFM2.5-8B-A1B-GGUF

model · LLM · by LiquidAI

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

other4.8 GB~7 GB RAMsource alive

507K downloads · 309 likes · numbers as of 2026-10-02
Qwen3-8B-GGUF

model · LLM · by Qwen

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers grou…

apache-2.04.7 GB~6 GB RAMsource alive

504K downloads · 305 likes · numbers as of 2026-10-02
Apodex-1.1-mini-GGUF

model · LLM · by abenzerps

GGUF quantizations of apodex/Apodex-1.1-mini, a 35.95B-parameter Qwen3.5 MoE model for research, data, files, code, and tool-driven work.

apache-2.020 GB~24 GB RAMsource alive

493K downloads · 18 likes · numbers as of 2026-10-02
gpt-oss-20b-GGUF

model · LLM · by unsloth

See our collection for all versions of gpt-oss including GGUF, 4-bit & 16-bit formats.

apache-2.011 GB~13 GB RAMsource alive

491K downloads · 849 likes · numbers as of 2026-10-02
Meta-Llama-3.1-8B-Instruct-GGUF

model · LLM · by bartowski

Llamacpp imatrix Quantizations of Meta-Llama-3.1-8B-Instruct

llama3.14.6 GB~6 GB RAMsource alive

485K downloads · 408 likes · numbers as of 2026-10-02
Qwen3.8-35B-A3B-Distill-GGUF

model · LLM · by empero-ai

GGUF quantizations of empero-ai/Qwen3.8-35B-A3B-Distill — a distillation of the Qwen3.8 frontier models into the Qwen3.6-35B-A3B Mixture-of-Experts architecture — for llama.cpp, Ollama, LM Studio, Ja…

apache-2.020 GB~24 GB RAMsource alive

479K downloads · 169 likes · numbers as of 2026-10-02
Qwen3-4B-GGUF

model · LLM · by Qwen

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers grou…

apache-2.02.3 GB~4 GB RAMsource alive

473K downloads · 173 likes · numbers as of 2026-10-02
Spark-X2.5-4B-GGUF

model · LLM · by XHToken

Spark-X2.5 is a compact, general-purpose language model for conversation, writing, translation, reasoning, coding, tool use, and agentic workflows. It uses a hybrid attention architecture, supports a…

apache-2.02.4 GB~4 GB RAMsource alive

466K downloads · 256 likes · numbers as of 2026-10-02
Parable-Qwen3-8B-Claude-Fable-5-GGUF

model · LLM · by AnkitAI

🪶 Parable-Qwen3-8B — trained on genuine Claude Fable 5 agent traces

apache-2.04.7 GB~6 GB RAMsource alive

456K downloads · 5 likes · numbers as of 2026-10-02
Qwen3-4B-GGUF

model · LLM · by unsloth

See our collection for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats.

apache-2.02.3 GB~4 GB RAMsource alive

442K downloads · 246 likes · numbers as of 2026-10-02
Ornith-1.0-9B-GGUF

model · LLM · by unsloth

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

mit5.3 GB~7 GB RAMsource alive

428K downloads · 63 likes · numbers as of 2026-10-02
Bonsai-27B-gguf

model · LLM · by prism-ml

Prism ML Website Whitepaper Demo & Examples Discord

apache-2.050 GB~59 GB RAMsource alive

426K downloads · 883 likes · numbers as of 2026-10-02
all-MiniLM-L6-v2-GGUF

model · Embeddings · by leliuga

all-MiniLM-L6-v2 - GGUF - Model creator: Sentence Transformers - Original model: all-MiniLM-L6-v2

apache-2.020 MB~1 GB RAMsource alive

418K downloads · 9 likes · numbers as of 2026-10-02
gemma-4-12B-coder-fable5-composer2.5-v1-GGUF

model · LLM · by yuxinlu1

💻 Gemma4-12B-Coder (GGUF) — Composer 2.5 × Fable 5 ✨ ### 🐣 Tiny footprint, big brain — a local coding model for everyone

apache-2.06.9 GB~9 GB RAMsource alive

406K downloads · 2.9K likes · numbers as of 2026-10-02
Voxtral-Mini-4B-Realtime-2602-gguf

model · Speech · by handy-computer

Voxtral-Mini-4B-Realtime-2602: transcribe.cpp GGUF

apache-2.02.6 GB~4 GB RAMsource alive

401K downloads · 6 likes · numbers as of 2026-10-02
DeepSeek-Coder-V2-Lite-Instruct-GGUF

model · LLM · by bartowski

Llamacpp imatrix Quantizations of DeepSeek-Coder-V2-Lite-Instruct

other9.7 GB~12 GB RAMsource alive

385K downloads · 195 likes · numbers as of 2026-10-02