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

alt.freeweights.*

Sections are families; modality is a filter. Official lab repos and base models come first, then by downloads. Order is never for sale.

6021 models · 11 datasets · 247 tools
SubjectSizeParamsLicenseDate
ltx-2.5-mlx-q8From the publisher From: mlx-community in alt.freeweights.video24.6 GB—Not reviewed2026-11-15gemma-4-e4b-it-bf16From the publisher From: mlx-community in alt.freeweights.gemma15.9 GB7.9BGated2026-11-15higgs-audio-v2-3B-mlx-q8From the publisher From: mlx-community in alt.freeweights.speech6.20 GB—Not reviewed2026-11-15fish-audio-drama-3-bf16From the publisher From: mlx-community in alt.freeweights.speech72.4 GB—Not reviewed2026-11-15Qwen2.5-0.5B-Instruct-abliterated-ONNXFrom the publisher From: onnx-community in alt.freeweights.abliterated6.46 GB—Not reviewed2026-11-15InternVL3-38B-Instruct-GGUFFrom the publisher From: unsloth in alt.freeweights.text524 GB—Not reviewed2026-11-15IndexTTS-2-MLXFrom the publisher From: mlx-community in alt.freeweights.speech4.33 GB—Not reviewed2026-11-15LFM2.5-1.2B-Thinking-MLX-bf16From the publisher From: lmstudio-community in alt.freeweights.lfm2.35 GB1.2BNot reviewed2026-11-15ltx-2.5-mlxFrom the publisher From: mlx-community in alt.freeweights.video111 GB—Not reviewed2026-11-15gemma-4-E2B-it-assistant-bf16From the publisher From: mlx-community in alt.freeweights.gemma190 MB78MGated2026-11-15Qwen2.5-Omni-3B-Thinker-4bitFrom the publisher From: mlx-community in alt.freeweights.qwen2.57 GB—Non-commercial2026-11-15NVIDIA-Nemotron-Nano-9B-v2-4bitsFrom the publisher From: mlx-community in alt.freeweights.nemotron5.02 GB1.4BNot reviewed2026-11-15Qwen2.5-Omni-3B-Thinker-8bitFrom the publisher From: mlx-community in alt.freeweights.qwen4.27 GB—Non-commercial2026-11-15gemma-4-e2b-4bitFrom the publisher From: mlx-community in alt.freeweights.gemma3.61 GB5.1BNot reviewed2026-11-15Llama-3.2-11B-Vision-Instruct-abliterated-4-bitFrom the publisher From: mlx-community in alt.freeweights.abliterated6.02 GB10.7BGated2026-11-15gemma-4-e4b-4bitFrom the publisher From: mlx-community in alt.freeweights.gemma5.25 GB8BNot reviewed2026-11-15gemma-4-31b-bf16From the publisher From: mlx-community in alt.freeweights.gemma62.6 GB31.3BNot reviewed2026-11-15gemma-4-31b-8bitFrom the publisher From: mlx-community in alt.freeweights.gemma33.8 GB31.3BNot reviewed2026-11-15Hy-MT2-1.8B-8bitFrom the publisher From: mlx-community in alt.freeweights.vision1.92 GB1.8BNot reviewed2026-11-15OmniVoice-4bitFrom the publisher From: mlx-community in alt.freeweights.speech1.14 GB316MNot reviewed2026-11-15Qwen2.5-Coder-14B-Instruct-abliterated-6bitFrom the publisher From: mlx-community in alt.freeweights.abliterated12.0 GB14.8BNot reviewed2026-11-15LFM2.5-Embedding-350M-bf16Hosted (signed) From: mlx-community in alt.freeweights.lfm714 MB354MCustom terms2026-11-15Llama-3.2-3B-FluxedFrom the publisher From: mlx-community in alt.freeweights.llama6.44 GB3.2BNot reviewed2026-11-15OmniVoiceFrom the publisher From: mlx-community in alt.freeweights.speech3.27 GB613MNot reviewed2026-11-15gemma-4-26b-a4b-4bitFrom the publisher From: mlx-community in alt.freeweights.gemma15.6 GB25.8BNot reviewed2026-11-15Hi3Dv1.0-mlxFrom the publisher From: mlx-community in alt.freeweights.text10.2 GB4.3BNot reviewed2026-11-15NVIDIA-Nemotron-Nano-9B-v2-6bitFrom the publisher From: mlx-community in alt.freeweights.nemotron7.24 GB1.9BNot reviewed2026-11-15Llama-3.2-11B-Vision-Instruct-abliterated-8-bitFrom the publisher From: mlx-community in alt.freeweights.abliterated11.4 GB10.7BGated2026-11-15Qwen2.5-72B-Instruct-8bitFrom the publisher From: mlx-community in alt.freeweights.qwen77.3 GB72.7BNot reviewed2026-11-15gemma-3-12b-it-8bitFrom the publisher From: mlx-community in alt.freeweights.gemma14.5 GB—Gated2026-11-15LFM2-350M-MLX-bf16Hosted (signed) From: lmstudio-community in alt.freeweights.lfm714 MB354MCustom terms2026-11-15Mistral-Small-Instruct-2409From the publisher From: unsloth in alt.freeweights.mistral44.5 GB22.2BNot reviewed2026-11-15gemma-3n-E2B-it-MLX-bf16From the publisher From: lmstudio-community in alt.freeweights.gemma10.9 GB5.4BGated2026-11-15functiongemma-270m-it-MLX-bf16From the publisher From: lmstudio-community in alt.freeweights.gemma570 MB268MGated2026-11-15Supra2-Nano-ONNXFrom the publisher From: onnx-community in alt.freeweights.text18.2 MB—Not reviewed2026-11-15LFM2-700M-MLX-bf16Hosted (signed) From: lmstudio-community in alt.freeweights.lfm1.49 GB742MCustom terms2026-11-15Home-FunctionGemma-270m-ONNXFrom the publisher From: onnx-community in alt.freeweights.gemma6.13 GB—Gated2026-11-15falcon-perception-onnx-webgpuFrom the publisher From: onnx-community in alt.freeweights.vision6.94 GB—Not reviewed2026-11-15mmarco-mMiniLMv2-L12-H384-v1From the publisher From: cross-encoder in alt.freeweights.embed4.15 GB118MNot reviewed2026-11-15Qwen2.5-VL-3B-Instruct-AWQFrom the publisher From: Qwen in alt.freeweights.qwen3.42 GB3.8BNot reviewed2026-11-15Kokoro-82M-v1.0-ONNXHosted (signed) From: onnx-community in alt.freeweights.speech1.45 GB—Permissive2026-11-14NVIDIA-Nemotron-3.5-Bolt-E4B-GGUFHosted (signed) From: unsloth in alt.freeweights.nemotron59.5 GB—Custom terms2026-11-15LTX-2.3-GGUFFrom the publisher From: unsloth in alt.freeweights.video1.08 TB—Not reviewed2026-11-15ms-marco-TinyBERT-L2-v2From the publisher From: cross-encoder in alt.freeweights.embed173 MB4MNot reviewed2026-11-15LFM2.5-24B-A2B-GGUFHosted (signed) From: unsloth in alt.freeweights.lfm171 GB—Custom terms2026-11-15Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUFHosted (signed) From: alesha-pro in alt.freeweights.abliterated295 GB—Custom terms2026-11-14thomsonreuters_Thomson-1.0-Small-GGUFFrom the publisher From: bartowski in alt.freeweights.text571 GB—Not reviewed2026-11-15Meta-Llama-3.1-8B-Instruct-GGUFFrom the publisher From: bartowski in alt.freeweights.llama143 GB—Gated2026-11-15Llama-3.2-3B-Instruct-GGUFFrom the publisher From: unsloth in alt.freeweights.llama61.4 GB—Gated2026-11-15Kimi-K3-GGUFFrom the publisher From: unsloth in alt.freeweights.kimi7.42 TB—Not reviewed2026-11-15nli-MiniLM2-L6-H768From the publisher From: cross-encoder in alt.freeweights.vision2.88 GB82MNot reviewed2026-11-15Llama-3.3-70B-Instruct-GGUFFrom the publisher From: bartowski in alt.freeweights.llama1.23 TB—Gated2026-11-15Qwen2.5-VL-3B-Instruct-GGUFFrom the publisher From: ggml-org in alt.freeweights.qwen13.6 GB—Not reviewed2026-11-15Llama-3.2-3B-Instruct-GGUFFrom the publisher From: bartowski in alt.freeweights.llama43.1 GB—Gated2026-11-15Llama-3.2-1B-Instruct-GGUFFrom the publisher From: bartowski in alt.freeweights.llama17.2 GB—Gated2026-11-15llava-1.5-7b-hf-bnb-4bitFrom the publisher From: unsloth in alt.freeweights.text4.04 GB7.3BGated2026-11-15Kimi-K2.5From the publisher From: mlx-community in alt.freeweights.kimi658 GB1.03TNot reviewed2026-11-15NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUFFrom the publisher From: ggml-org in alt.freeweights.nemotron538 GB—Not reviewed2026-11-15TheDrummer_Artemis-31B-v1.2-GGUFFrom the publisher From: bartowski in alt.freeweights.text496 GB—Not reviewed2026-11-15Meta-Llama-3.1-8B-Instruct-bnb-4bitFrom the publisher From: unsloth in alt.freeweights.llama5.72 GB8.2BGated2026-11-15Kokoro-82M-ONNXFrom the publisher From: onnx-community in alt.freeweights.speech1.42 GB—Not reviewed2026-11-15tinygemma3-GGUFFrom the publisher From: ggml-org in alt.freeweights.gemma48.6 MB—Not reviewed2026-11-15Qwen2.5-Coder-14B-Instruct-abliterated-GGUFFrom the publisher From: bartowski in alt.freeweights.abliterated242 GB—Not reviewed2026-11-15TheDrummer_Orion-26B-A4B-v1.1-GGUFFrom the publisher From: bartowski in alt.freeweights.text426 GB—Not reviewed2026-11-15Meta-Llama-3.1-8B-Instruct-GGUFFrom the publisher From: lmstudio-community in alt.freeweights.llama34.6 GB—Gated2026-11-15Llama-3.2-3B-Instruct-GGUFFrom the publisher From: lmstudio-community in alt.freeweights.llama9.90 GB—Gated2026-11-15Llama-3.2-1B-Instruct-GGUFFrom the publisher From: unsloth in alt.freeweights.llama24.9 GB—Gated2026-11-15LFM2.5-1.2B-Instruct-MLX-8bitFrom the publisher From: lmstudio-community in alt.freeweights.lfm1.25 GB1.2BNot reviewed2026-11-15Anima-LLLiteFrom the publisher From: Comfy-Org in alt.freeweights.image244 MB—Non-commercial2026-11-15LFM2.5-1.2B-Instruct-MLX-4bitFrom the publisher From: lmstudio-community in alt.freeweights.lfm663 MB1.2BNot reviewed2026-11-15NVIDIA-Nemotron-3-Nano-4B-GGUFFrom the publisher From: lmstudio-community in alt.freeweights.nemotron11.0 GB—Not reviewed2026-11-15LFM2.5-1.2B-Instruct-MLX-6bitFrom the publisher From: lmstudio-community in alt.freeweights.lfm956 MB1.2BNot reviewed2026-11-15Llama-3.3-70B-Instruct-abliterated-GGUFFrom the publisher From: bartowski in alt.freeweights.abliterated928 GB—Gated2026-11-15LTX-2-GGUFFrom the publisher From: unsloth in alt.freeweights.video304 GB—Not reviewed2026-11-15cognitivecomputations_Dolphin3.0-Mistral-24B-GGUFFrom the publisher From: bartowski in alt.freeweights.mistral422 GB—Not reviewed2026-11-15LiquidAI_LFM2.5-1.2B-Instruct-GGUFFrom the publisher From: bartowski in alt.freeweights.lfm18.6 GB—Not reviewed2026-11-15NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUFHosted (signed) From: unsloth in alt.freeweights.nemotron867 GB—Custom terms2026-11-15TheDrummer_Cydonia-24B-v4.3-GGUFFrom the publisher From: bartowski in alt.freeweights.text377 GB—Not reviewed2026-11-15Llama-3.2-3B-Instruct-uncensored-GGUFFrom the publisher From: bartowski in alt.freeweights.llama57.4 GB—Not reviewed2026-11-15Qwen2.5-VL-3B-Instruct-GGUFFrom the publisher From: unsloth in alt.freeweights.qwen57.5 GB—Not reviewed2026-11-15Nemotron-3-Nano-30B-A3B-GGUFFrom the publisher From: unsloth in alt.freeweights.nemotron576 GB—Not reviewed2026-11-15Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUFFrom the publisher From: lmstudio-community in alt.freeweights.nemotron93.2 GB—Not reviewed2026-11-15Llama-4-Scout-17B-16E-Instruct-GGUFFrom the publisher From: unsloth in alt.freeweights.llama1.80 TB—Gated2026-11-15Meta-Llama-3.1-70B-Instruct-GGUFFrom the publisher From: bartowski in alt.freeweights.llama863 GB—Gated2026-11-15Llama-3.3-70B-Instruct-GGUFFrom the publisher From: unsloth in alt.freeweights.llama1.34 TB—Gated2026-11-15Hermes-4-70B-MLX-4bitFrom the publisher From: lmstudio-community in alt.freeweights.text39.7 GB70.6BGated2026-11-15LFM2.5-1.2B-Instruct-GGUFFrom the publisher From: unsloth in alt.freeweights.lfm16.3 GB—Not reviewed2026-11-15Hermes-4-70B-MLX-8bitFrom the publisher From: lmstudio-community in alt.freeweights.text75.0 GB70.6BGated2026-11-15gemma-2-2b-it-abliterated-GGUFFrom the publisher From: bartowski in alt.freeweights.abliterated36.3 GB—Gated2026-11-15Hermes-4-70B-MLX-6bitFrom the publisher From: lmstudio-community in alt.freeweights.text57.3 GB70.6BGated2026-11-15Hermes-4-70B-MLX-5bitFrom the publisher From: lmstudio-community in alt.freeweights.text48.5 GB70.6BGated2026-11-15TheDrummer_Magidonia-24B-v4.3-GGUFFrom the publisher From: bartowski in alt.freeweights.text377 GB—Not reviewed2026-11-15Kimi-K2.5-GGUFFrom the publisher From: unsloth in alt.freeweights.kimi16.8 TB—Not reviewed2026-11-15Llama-3.2-3B-Instruct-unsloth-bnb-4bitFrom the publisher From: unsloth in alt.freeweights.llama2.37 GB3.3BGated2026-11-15Qwen2.5-Coder-32B-Instruct-abliterated-GGUFFrom the publisher From: bartowski in alt.freeweights.abliterated527 GB—Not reviewed2026-11-15Llama-3.2-1B-Instruct-unsloth-bnb-4bitFrom the publisher From: unsloth in alt.freeweights.llama1.12 GB1.3BGated2026-11-15Meta-Llama-3.1-8B-Instruct-unsloth-bnb-4bitFrom the publisher From: unsloth in alt.freeweights.llama5.98 GB8.2BGated2026-11-15Dolphin3.0-Llama3.1-8B-GGUFFrom the publisher From: bartowski in alt.freeweights.llama155 GB—Gated2026-11-15Llama-4-Maverick-17B-128E-Instruct-GGUFFrom the publisher From: unsloth in alt.freeweights.llama6.62 TB—Gated2026-11-15ms-marco-TinyBERT-L2From the publisher From: cross-encoder in alt.freeweights.embed173 MB4MNot reviewed2026-11-15

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

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