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.
-
Qwen2.5-32B-Instruct-GGUF
model · LLM · by bartowski
Llamacpp imatrix Quantizations of Qwen2.5-32B-Instruct
apache-2.018 GB~22 GB RAMsource alive
379K downloads · 76 likes · numbers as of 2026-10-02
-
Ternary-Bonsai-8B-gguf
model · LLM · by prism-ml
Prism ML Website White Paper Demo & Examples Discord
apache-2.015 GB~19 GB RAMsource alive
371K downloads · 164 likes · numbers as of 2026-10-02
-
Qwen3.6-35B-A3B-NVFP4-MTP-GGUF
model · LLM · by michaelw9999
This repo contains two experimental NVFP4 GGUF quantizations of Qwen3.6-35B-A3B for llama.cpp. This was quantized using my experimental advanced-gguf-quantizer tool. Both models were imatrix calibrat…
license unknown19 GB~23 GB RAMsource alive
365K downloads · 12 likes · numbers as of 2026-10-02
-
Qwen-AgentWorld-35B-A3B-GGUF
model · LLM · by unsloth
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.
apache-2.021 GB~25 GB RAMsource alive
354K downloads · 247 likes · numbers as of 2026-10-02
-
LFM2.5-1.2B-Instruct-GGUF
model · LLM · by LiquidAI
LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
other697 MB~2 GB RAMsource alive
351K downloads · 224 likes · numbers as of 2026-10-02
-
Parable-Qwen3-4B-Claude-Fable-5-GGUF
model · LLM · by AnkitAI
A 4B local coding model with agent instincts. Planning, tool habits and terminal reasoning distilled from real Claude Fable 5 agent sessions, not synthetic Q&A. Runs on ~2.5 GB of RAM.
apache-2.02.3 GB~4 GB RAMsource alive
349K downloads · 19 likes · numbers as of 2026-10-02
-
Qwen3-0.6B-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-2.0610 MB~2 GB RAMsource alive
345K downloads · 88 likes · numbers as of 2026-10-02
-
whisper-large-v3-turbo-gguf
model · Speech · by handy-computer
whisper-large-v3-turbo: transcribe.cpp GGUF
apache-2.0511 MB~2 GB RAMsource alive
341K downloads · 4 likes · numbers as of 2026-10-02
-
nemotron-speech-streaming-en-0.6b
model · Speech · by nvidia
June 4, 2026: New multilingual model released: NVIDIA Nemotron 3.5 ASR Streaming 0.6B extends this English streaming ASR model to 40 language-locales in a single 600M-parameter model. It supports lan…
other667 MB~2 GB RAMsource alive
332K downloads · 632 likes · numbers as of 2026-10-02
-
GLM-5.2-GGUF
model · LLM · by unsloth
See Unsloth Dynamic 2.0 GGUFs for our quantization benchmarks.
mit9 MB~1 GB RAMsource alive
324K downloads · 647 likes · numbers as of 2026-10-02
-
parakeet-ctc-1.1b
model · Speech · by nvidia
parakeet-ctc-1.1b is an ASR model that transcribes speech in lower case English alphabet. This model is jointly developed by NVIDIA NeMo and Suno.ai teams. It is an XXL version of FastConformer CTC […
cc-by-4.01.1 GB~2 GB RAMsource alive
318K downloads · 61 likes · numbers as of 2026-10-02
-
Qwen2.5-Coder-7B-Instruct-GGUF
model · LLM · by Qwen
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 bi…
apache-2.04.4 GB~6 GB RAMsource alive
317K downloads · 505 likes · numbers as of 2026-10-02
-
TwIL-LM3
model · LLM · by webAI-Official
A 3B reasoning model for formal logic tasks, built from HuggingFaceTB/SmolLM3-3B through LoRA supervised fine-tuning, checkpoint fusion, WiSE-FT weight interpolation, and entropy-weighted GRPO reinfo…
other1.8 GB~3 GB RAMsource alive
315K downloads · 92 likes · numbers as of 2026-10-02
-
Kwaipilot_KAT-Coder-V2.5-Dev-GGUF
model · LLM · by bartowski
Llamacpp imatrix Quantizations of KAT-Coder-V2.5-Dev by Kwaipilot
apache-2.020 GB~24 GB RAMsource alive
313K downloads · 138 likes · numbers as of 2026-10-02
-
nomic-embed-text-v1.5-GGUF
model · Embeddings · by nomic-ai
Embedding text with nomic-embed-text requires task instruction prefixes at the beginning of each string.
apache-2.080 MB~1 GB RAMsource alive
313K downloads · 137 likes · numbers as of 2026-10-02
-
whisper-large-v3-gguf
model · Speech · by handy-computer
GGUF conversions of openai/whisper-large-v3 for use with transcribe.cpp.
apache-2.0951 MB~2 GB RAMsource alive
313K downloads · 2 likes · numbers as of 2026-10-02
-
llm-jp-4-33b-thinking-gguf
model · LLM · by llm-jp
LLM-jp-4 is a series of large language models developed by the Research and Development Center for Large Language Models at the National Institute of Informatics.
apache-2.019 GB~23 GB RAMsource alive
310K downloads · 11 likes · numbers as of 2026-10-02
-
POCKET-26B-GGUF
model · LLM · by FINAL-Bench
🆕 POCKET-Qwen3.8-Flash-Next — a 180B model running on a laptop with 8 GB VRAM + 32 GB RAM · 4.17 tok/s measured. >
apache-2.016 GB~19 GB RAMsource alive
296K downloads · 58 likes · numbers as of 2026-10-02
-
Qwopus3.6-27B-Fusion-GGUF
model · LLM · by KyleHessling1
▶ PLAY ORBITAL — a game this model built, live in your browser ◀
other16 GB~19 GB RAMsource alive
292K downloads · 78 likes · numbers as of 2026-10-02
-
Qwen3-0.6B-GGUF
model · LLM · by MaziyarPanahi
MaziyarPanahi/Qwen3-0.6B-GGUF - Model creator: Qwen - Original model: Qwen/Qwen3-0.6B
license unknown462 MB~2 GB RAMsource alive
289K downloads · 15 likes · numbers as of 2026-10-02
-
Jan-v3.5-4B-gguf
model · LLM · by janhq
Jan-v3.5-4B is a fine-tuned variant of Jan-v3-4B-base-instruct, specialized on math reasoning and identity datasets. It retains the general-purpose capabilities of the base model while delivering imp…
apache-2.02.5 GB~4 GB RAMsource alive
285K downloads · 38 likes · numbers as of 2026-10-02
-
canary-180m-flash-gguf
model · Speech · by handy-computer
GGUF conversions of nvidia/canary-180m-flash for use with transcribe.cpp.
cc-by-4.0133 MB~1 GB RAMsource alive
268K downloads · 0 likes · numbers as of 2026-10-02
-
mxbai-embed-large-v1-gguf
model · Embeddings · by ChristianAzinn
This is our base sentence embedding model. It was trained using AnglE loss on our high-quality large scale data. It achieves SOTA performance on BERT-large scale. Find out more in our blog post.
apache-2.0206 MB~1 GB RAMsource alive
239K downloads · 8 likes · numbers as of 2026-10-02
-
bge-small-en-v1.5-GGUF
model · Embeddings · by unsloth
embedding model by unsloth, gguf files on Hugging Face.
mit64 MB~1 GB RAMsource alive
206K downloads · 5 likes · numbers as of 2026-10-02