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

Needs a workstation

Models whose smallest good build needs more than 12 GB (file size x 1.2 + 0.4 GB): a GPU with plenty of memory, or a Mac or PC with 32 GB or more. 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

Sectiontext151qwen112mistral27granite24olmo19nemotron18

Show 15 more

deepseek15glm15gemma13lfm11mimo9image7phi7gpt-oss6vision6abliterated5minicpm4kimi2llama2embed1speech1

Tasktext generation280image text to text105not tagged34text to image12any to any11image to image3

Show 7 more

zero shot classification3text classification2audio text to text1image text to image1sentence similarity1text to speech1translation1

License classPermissive426Custom terms28Gated (link only)1

Formatsafetensors430gguf25onnx4

Size4 to 40 GB17640 to 200 GB203200 GB and up76

ListingHosted (signed)454From the publisher · Gated1

Bytes fromFrom source454From the publisher1

TermsNo extra terms426Requires accepting terms29

ParametersUnder 1B33B to 6B76B to 9B869B to 12B2112B to 24B7924B to 32B70

Show 5 more

32B to 64B7764B to 128B31128B to 500B37Over 500B21Not stated23

Librarysafetensors430transformers352MLX44GGUF28diffusers14PyTorch8

Show 4 more

ONNX4PEFT4Transformers.js2sentence-transformers1

LanguageEnglish210Chinese94German50Spanish50French49Japanese46

Show 60 more

Korean44Italian42Portuguese42Arabic39Russian30Hindi27Polish22Indonesian21Vietnamese21Multilingual17Turkish17Ukrainian17Bangla16Malay16Romanian16Swedish16Persian15Serbian14Nepali13Dutch13Thai8Czech6Bulgarian3Danish3Greek3Estonian3Finnish3Hebrew3Croatian3Hungarian3Lithuanian3Latvian3Norwegian3Slovak3Slovenian3Tamil3Telugu3Catalan2Irish2Gujarati2Khmer2Marathi2Maltese2Burmese2Punjabi2Filipino2Urdu2Tibetan1Galician1Icelandic1Javanese1Kazakh1Kannada1Lao1Malayalam1Mongolian1Odia1Pali1Sundanese1Uyghur1

AppsSGLang378vLLM378Jan25llama.cpp25LM Studio25Ollama25

Show 2 more

DiffusionBee15Draw Things15

Runs on Allternit CloudYes, served by Allternit Cloud1

On devicePhone10Laptop197Workstation455In the browser9

Enginellama.cpp389mlx198webgpu23

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

455 models

SubjectSizeParamsLicenseDate

MOSS-Image-SFTHosted (signed) From: OpenMOSS-Team in alt.freeweights.image27.2 GB5.1BPermissive2026-11-15 Nanbeige4.3-33BHosted (signed) From: Nanbeige in alt.freeweights.text66.3 GB33.1BPermissive2026-11-15 Teutonic-I-Reliquary-RLHosted (signed) From: ReliquaryForge in alt.freeweights.text17.9 GB9BPermissive2026-11-15

gpt-oss-20b-BF16Hosted (signed) From: unsloth in alt.freeweights.gpt-oss41.9 GB20.9BPermissive2026-11-15

Qwen-Image-2512-4bitHosted (signed) From: mlx-community in alt.freeweights.qwen25.9 GB—Permissive2026-11-15 Mellum2.1-12B-A2.5B-ThinkingHosted (signed) From: JetBrains in alt.freeweights.text24.3 GB12.1BPermissive2026-11-15

Qwen3.5-35B-A3B-4bitHosted (signed) From: mlx-community in alt.freeweights.qwen20.4 GB35.1BPermissive2026-11-15

Qwen3.5-122B-A10B-4bitHosted (signed) From: mlx-community in alt.freeweights.qwen69.6 GB122.6BPermissive2026-11-15 Mellum2-12B-A2.5B-InstructHosted (signed) From: JetBrains in alt.freeweights.text24.3 GB12.1BPermissive2026-11-15 MLExpertHosted (signed) From: InternScience in alt.freeweights.text69.4 GB34.7BPermissive2026-11-15 Apriel-Nemotron-15b-ThinkerHosted (signed) From: ServiceNow-AI in alt.freeweights.nemotron30.0 GB15BPermissive2026-11-15

Qwen3.5-27B-4bitHosted (signed) From: mlx-community in alt.freeweights.qwen16.1 GB27.4BPermissive2026-11-15 Kolibri-1-BF16Hosted (signed) From: Aleph-Alpha in alt.freeweights.text156 GB78.1BPermissive2026-11-15 gpt-oss-20b-hereticHosted (signed) From: p-e-w in alt.freeweights.abliterated41.9 GB20.9BPermissive2026-11-15 Terminal-RSI-27BHosted (signed) From: Teriminal-RSI in alt.freeweights.text55.6 GB27.8BPermissive2026-11-15

Mistral-Nemo-Instruct-2407-GGUFHosted (signed) From: unsloth in alt.freeweights.mistral74.7 GB—Permissive2026-11-15

Mistral-Small-4-119B-2603-4bitHosted (signed) From: mlx-community in alt.freeweights.mistral67.8 GB119.4BPermissive2026-11-15 Groot-19B-A3B-261023Hosted (signed) From: GrootTeam in alt.freeweights.text38.9 GB19.4BPermissive2026-11-15

Qwen3.5-122B-A10B-bf16Hosted (signed) From: mlx-community in alt.freeweights.qwen245 GB122.6BPermissive2026-11-15 Darwin-36B-OpusHosted (signed) From: FINAL-Bench in alt.freeweights.text69.4 GB34.7BPermissive2026-11-15

Qwen3.5-35B-A3B-bf16Hosted (signed) From: mlx-community in alt.freeweights.qwen70.2 GB35.1BPermissive2026-11-15

Qwen3.5-35B-A3B-8bitHosted (signed) From: mlx-community in alt.freeweights.qwen37.7 GB35.1BPermissive2026-11-15

Qwen3.5-27B-bf16Hosted (signed) From: mlx-community in alt.freeweights.qwen54.7 GB27.4BPermissive2026-11-15 magnum-v4-72bHosted (signed) From: anthracite-org in alt.freeweights.text145 GB72.7BPermissive2026-11-15 SenseNova-6.8-Code2VideoHosted (signed) From: sensenova in alt.freeweights.text54.9 GB27.4BPermissive2026-11-15

Qwen3-Omni-30B-A3B-Instruct-4bitHosted (signed) From: mlx-community in alt.freeweights.qwen21.8 GB35.3BPermissive2026-11-15

gpt-oss-120b-4bitHosted (signed) From: mlx-community in alt.freeweights.gpt-oss65.8 GB116.8BPermissive2026-11-15 marin-32b-baseHosted (signed) From: marin-community in alt.freeweights.text130 GB32.5BPermissive2026-11-15

Qwen3.5-122B-A10B-6bitHosted (signed) From: mlx-community in alt.freeweights.qwen100 GB122.6BPermissive2026-11-15

Devstral-Small-2507-MLX-bf16Hosted (signed) From: lmstudio-community in alt.freeweights.mistral47.2 GB23.6BPermissive2026-11-15 EuroLLM-22B-Instruct-2512Hosted (signed) From: utter-project in alt.freeweights.text45.3 GB22.6BPermissive2026-11-15

Qwen3.8-27B-bf16Hosted (signed) From: mlx-community in alt.freeweights.qwen54.7 GB27.4BPermissive2026-11-15

Qwen-Image-2512-8bitHosted (signed) From: mlx-community in alt.freeweights.qwen36.1 GB—Permissive2026-11-15

magistral-small-2506-mlx-bf16Hosted (signed) From: lmstudio-community in alt.freeweights.mistral47.2 GB23.6BPermissive2026-11-15 basal-omni-1.0-ultraHosted (signed) From: Remek in alt.freeweights.text62.6 GB31.3BPermissive2026-11-15 pplx-decider-v1.1-27bHosted (signed) From: perplexity-ai in alt.freeweights.vision52.2 GB26.1BPermissive2026-11-15 Baichuan-M2-32BHosted (signed) From: baichuan-inc in alt.freeweights.text67.1 GB32.8BPermissive2026-11-15 RuBio-27BHosted (signed) From: mulkzz in alt.freeweights.text55.6 GB27.8BPermissive2026-11-15

LFM2.5-24B-A2BHosted (signed) From: unsloth in alt.freeweights.lfm48.0 GB24BCustom terms2026-11-15 Sailor2-8B-ChatHosted (signed) From: sail in alt.freeweights.text17.1 GB8.5BPermissive2026-11-15

Qwen3.6-35B-A3B-bf16Hosted (signed) From: mlx-community in alt.freeweights.qwen70.2 GB35.1BPermissive2026-11-15 gemma-4-31B-it-uncensored-hereticHosted (signed) From: llmfan46 in alt.freeweights.abliterated62.6 GB31.3BPermissive2026-11-15 DeepSeek-V4-Pro-Qwen3.5-9BHosted (signed) From: Jackrong in alt.freeweights.qwen19.3 GB9.7BPermissive2026-11-15

NVIDIA-Nemotron-3.5-Super-VL-120B-A12BHosted (signed) From: unsloth in alt.freeweights.nemotron249 GB124.5BCustom terms2026-11-15 WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7BHosted (signed) From: WhiteRabbitNeo in alt.freeweights.qwen15.2 GB7.6BPermissive2026-11-15 Apex-35B-V1.0Hosted (signed) From: Apexintelligence-AI in alt.freeweights.text71.9 GB36BPermissive2026-11-15 cogito-v1-preview-qwen-14BHosted (signed) From: deepcogito in alt.freeweights.qwen29.5 GB14.8BPermissive2026-11-15

Muse-Glimmer-30B-bf16Hosted (signed) From: mlx-community in alt.freeweights.text59.6 GB29.8BPermissive2026-11-15 LiquidCode-2.5-24B-A2BHosted (signed) From: ItachiSan in alt.freeweights.text54.8 GB24BCustom terms2026-11-15

Qwen3.5-9B-bf16Hosted (signed) From: mlx-community in alt.freeweights.qwen18.8 GB9.4BPermissive2026-11-15 Qwen3.8-27B-piHosted (signed) From: bytkim in alt.freeweights.qwen59.4 GB27.8BPermissive2026-11-15 MindLink-32B-0801Hosted (signed) From: Skywork in alt.freeweights.text65.5 GB32.8BPermissive2026-11-15

Mistral-Small-3.1-24B-Instruct-2503-4bitHosted (signed) From: mlx-community in alt.freeweights.mistral14.1 GB—Permissive2026-11-15 Qwopus3.8-27B-Coder-FlashHosted (signed) From: Jackrong in alt.freeweights.text55.6 GB27.8BPermissive2026-11-15

gemma-4-31b-it-bf16Hosted (signed) From: mlx-community in alt.freeweights.gemma62.6 GB31.3BPermissive2026-11-15

← PreviousPage 4 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: InternScience <huggingface.co/InternScience>Newsgroups: alt.freeweights.textSubject: Sage-A1.5Date: 2026-11-15Commit: 0e3205cSigned: 2DC28CC7B26A283B ✓

Text generation model with 36B parameters. Safetensors weights, 71.9 GB in all. Published by InternScience under Apache-2.0.

36B params71.9GBSage-A1.5safetensorspermissive

FactsParams36BSize71.9 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get InternScience/Sage-A1.5
# manifest sha256 c01aefa45880… · 71.9 GB · 30 files
$ fw verify ./Sage-A1.5 InternScience/Sage-A1.5

Open model page

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