alt.freeweights.* · 29 sections · 8900 models listed (2868 shown under their base as variants) · collection

Runs on a phone

Models with a 4-bit or better build that needs about 1.8 GB or less (file size x 1.2 + 0.4 GB), the room an iPhone gives an app without the increased memory limit. Hand-picked models come first.

Filters

Sections

alt.freeweights.*6279 qwen655 deepseek82 kimi34 glm182 minimax29 mimo11 gemma376 gpt-oss9 olmo575 nemotron109 phi66 mistral118 granite162 smollm49 minicpm106 llama254 lfm74 text1134 speech186 embed219 vision1225 image199 video73 music16 ocr1 datasets11 tools247 abliterated77 allternit

Collections

Runs on a 256 GB Mac3692 Small enough for a laptop2556 Embeddings and rerankers290 Speech276 GGUF for llama.cpp and Ollama694 Open datasets11 Runs on a phone450 Runs on a laptop864 Needs a workstation455 Runs in the browser338

Filter

Sectionvision157embed67text59speech41qwen35lfm24

Show 10 more

granite23minicpm14smollm11nemotron6olmo6abliterated2llama2deepseek1gemma1glm1

Tasktext generation106automatic speech recognition44sentence similarity39image text to text35feature extraction32image classification23

Show 24 more

object detection22text classification22token classification17fill mask13zero shot image classification11not tagged10zero shot classification10image feature extraction9text ranking8image segmentation7question answering6text to speech6image to text5translation5zero shot object detection5keypoint detection3audio classification2mask generation2summarization2voice activity detection2any to any1audio text to text1depth estimation1time series forecasting1

License classPermissive416Custom terms33License not reviewed (link only)1

Formatsafetensors419onnx84gguf27openvino7coreml4ggml4

Show 2 more

ctranslate21mlx1

SizeUnder 4 GB3794 to 40 GB6940 to 200 GB2

ListingHosted (signed)449From the publisher · License not reviewed1

Bytes fromFrom source449From the publisher1

TermsNo extra terms416Requires accepting terms34

ParametersUnder 1B3521B to 3B78Not stated20

Librarysafetensors419transformers356PyTorch139ONNX84sentence-transformers74Transformers.js38

Show 10 more

JAX33GGUF27MLX24timm11OpenVINO7Core ML4GGML4CTranslate21open_clip1PEFT1

LanguageEnglish268German86French86Chinese86Spanish81Japanese77

Show 110 more

Italian65Portuguese64Arabic62Korean62Multilingual52Russian52Dutch48Polish47Hindi46Swedish44Vietnamese44Turkish42Thai40Danish39Greek39Hebrew38Czech37Finnish37Indonesian37Romanian37Ukrainian37Bulgarian36Hungarian35Latvian35Slovenian35Estonian34Persian34Lithuanian34Slovak34Croatian33Swahili33Marathi32Malay32Urdu32Bangla31Georgian31Albanian30Serbian30Catalan29Burmese29Norwegian29Tamil29Telugu29Filipino29Azerbaijani28Galician28Gujarati28Armenian28Icelandic28Kazakh28Macedonian28Mongolian28Welsh27Afrikaans26Belarusian26Khmer26Kannada26Malayalam26Basque25Nepali25Punjabi25Latin23Uzbek23Lao22Sinhala22Breton21Bosnian21Malagasy21Amharic20Somali20Haitian Creole19Sundanese19Yoruba19Pashto17Assamese16Hausa16Javanese16Sanskrit16Sindhi16Tatar16Yiddish16Norwegian Nynorsk15Occitan15Tajik15Bashkir13Kyrgyz13Maltese13Luxembourgish12Tibetan11Irish11Faroese10Lingala10Māori10Shona10Turkmen10Esperanto8Kurdish8Norwegian Bokmål8Xhosa8Uyghur7Western Frisian6Scottish Gaelic6Oromo6Odia6Volapük5Quechua4Aragonese3Chechen3Chuvash3Ido3

AppsSGLang136vLLM136llama.cpp22LM Studio22Ollama22Jan16

Show 1 more

whisper.cpp7

On devicePhone450Laptop450Workstation2In the browser345

Enginewebgpu355llama.cpp128mlx70

all 6279 Runs on a 256 GB Mac 3692 Small enough for a laptop 2556 Embeddings and rerankers 290 Speech 276 GGUF for llama.cpp and Ollama 694 Open datasets 11 Runs on a phone 450 Runs on a laptop 864 Needs a workstation 455 Runs in the browser 338 qwen 655 deepseek 82 kimi 34 glm 182 minimax 29 mimo 11 gemma 376 gpt-oss 9 olmo 575 nemotron 109 phi 66 mistral 118 granite 162 smollm 49 minicpm 106 llama 254 lfm 74 text 1134 speech 186 embed 219 vision 1225 image 199 video 73 music 16 ocr 1 datasets 11 tools 247 abliterated 77

Search models/

Sort

450 models

SubjectSizeParamsLicenseDate

Qwen2-0.5B-InstructHosted (signed) From: Qwen in alt.freeweights.qwen1,000 MB494MPermissive2026-11-15 granite-4.0-1b-speechHosted (signed) From: ibm-granite in alt.freeweights.granite4.64 GB2.3BPermissive2026-11-14 LFM2.5-350MHosted (signed) From: LiquidAI in alt.freeweights.lfm714 MB354MCustom terms2026-11-15

Qwen2.5-Math-1.5B-InstructHosted (signed) From: Qwen in alt.freeweights.qwen3.10 GB1.5BPermissive2026-11-15 MiniCPM-OCR-1.0Hosted (signed) From: openbmb in alt.freeweights.minicpm2.62 GB1.3BPermissive2026-11-14 gte-modernbert-baseHosted (signed) From: Alibaba-NLP in alt.freeweights.embed2.53 GB149MPermissive2026-11-14 modernbert-embed-baseHosted (signed) From: nomic-ai in alt.freeweights.embed2.53 GB149MPermissive2026-11-14 LFM3-1.7BHosted (signed) From: LiquidAI in alt.freeweights.lfm3.48 GB1.7BCustom terms2026-11-15

Qwen2.5-Math-1.5BHosted (signed) From: Qwen in alt.freeweights.qwen3.10 GB1.5BPermissive2026-11-15

Qwen2.5-Coder-0.5B-InstructHosted (signed) From: Qwen in alt.freeweights.qwen1,000 MB494MPermissive2026-11-15 SmolVLM2-2.2B-InstructHosted (signed) From: HuggingFaceTB in alt.freeweights.smollm8.99 GB2.2BPermissive2026-11-14

OLMo-2-0425-1B-InstructHosted (signed) From: allenai in alt.freeweights.olmo2.98 GB1.5BPermissive2026-11-14 InternVL3-1BHosted (signed) From: OpenGVLab in alt.freeweights.text1.89 GB938MPermissive2026-11-15 LFM2.5-VL-450MHosted (signed) From: LiquidAI in alt.freeweights.lfm902 MB449MCustom terms2026-11-15 granite-4.0-1bHosted (signed) From: ibm-granite in alt.freeweights.granite3.27 GB1.6BPermissive2026-11-14 granite-speech-4.1-2bHosted (signed) From: ibm-granite in alt.freeweights.granite4.87 GB2.3BPermissive2026-11-14

OpenReasoning-Nemotron-1.5BHosted (signed) From: nvidia in alt.freeweights.nemotron3.10 GB1.5BPermissive2026-11-15 LFM2-350M-ExtractHosted (signed) From: LiquidAI in alt.freeweights.lfm1.42 GB354MCustom terms2026-11-15 LFM2-1.2B-RAGHosted (signed) From: LiquidAI in alt.freeweights.lfm2.35 GB1.2BCustom terms2026-11-15 LFM2-350M-MathHosted (signed) From: LiquidAI in alt.freeweights.lfm714 MB354MCustom terms2026-11-15

Qwen3-ASR-0.6B-8bitHosted (signed) From: mlx-community in alt.freeweights.qwen1.01 GB782MPermissive2026-11-15 rtdetr_v2_r18vdHosted (signed) From: PekingU in alt.freeweights.vision80.9 MB20MPermissive2026-11-15 tinyroberta-squad2Hosted (signed) From: deepset in alt.freeweights.vision655 MB82MPermissive2026-11-15

← PreviousPage 3 of 5Next →

Slide, drag, or use the arrow keys.

No model matches these filters.Remove a filter or search for something shorter.

Every row is downloadable or links to its source. Press / to search, n and p to move in the list.

From:

Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject: Qwen2-0.5B-InstructDate: 2026-11-15Commit: c540970Signed: 2DC28CC7B26A283B ✓

Text generation model with 494M parameters. Safetensors weights, 1,000 MB in all. Published by Qwen under Apache-2.0.

494M params

1,000MBQwen2-0.5B-Instructsafetensorspermissive

FactsParams494MSize1,000 MBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get Qwen/Qwen2-0.5B-Instruct
# manifest sha256 2ef0a343d842… · 1,000 MB · 10 files
$ fw verify ./Qwen2-0.5B-Instruct Qwen/Qwen2-0.5B-Instruct

Open model page

Goal 1: 45 USD, 3 months x 15 USD; or a verified free VM0% fundedREADME: operating statementAllternit, the open source alternative