AIUnzipped — AI news that makes sense

AIUnzippedAI news and analysis

Model Discovery

Synced 9/18/2026, 8:26:49 PM

78 results · clear all

All Language Image Audio Video Multimodal Embeddings Other

All 💻 CPU-friendly 🖥️ GPU required ⚡ Either

All GGUF MLX ONNX AWQ GPTQ FP16 TFLite Llamafile

Any ≤4 GB ≤8 GB ≤16 GB ≤32 GB 32 GB+

All 🟢 Open 🔒 Restricted

visualrl-qwen3vl4b-ppo1-4bx-c50-hires-fixNEW

by Miiche

⚡ CPU/GPU~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

visualrl-qwen3vl2b-ppo1-visionsr1-r11-fixNEW

by Miiche

⚡ CPU/GPU~5 GB2B params

⬇ 0♥ 0

Other

View on Hugging Face

qwen35-9b-qwen-embedding-rag-loraNEW

by vamsee9201

🖥️ GPUFP16~22 GB9B params

⬇ 0♥ 0

Other

View on Hugging Face

4b-C-solvability-200-luna-8k-epoch3NEW

by Stage-jh-monitor

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

undo-qwen3-4bNEW

by QQSHI13

⚡ CPU/GPU~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

LFM2.5-350M-Hexagon-w8a16NEW

by TaksheelS

💻 CPUONNX~2 GB350M params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

by bimabk

🖥️ GPUFP16~3 GB1B params

⬇ 0♥ 0

Other

View on Hugging Face

ftbench-qlora-llama3.2-3bNEW

by najahaja

⚡ CPU/GPU~8 GB3B params

⬇ 0♥ 0

Other

View on Hugging Face

4b-A-solvability-200-luna-8k-epoch3NEW

by Stage-org

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

Affine-5h2nsvpewy-v3bNEW

by isomsom

🖥️ GPUFP16~8 GB3B params

⬇ 0♥ 0

Other

View on Hugging Face

lingbot-vla-v2-6b-lerobot-robotwinNEW

by miracle-techlink

⚡ CPU/GPU~15 GB6B params

⬇ 0♥ 0

Other

View on Hugging Face

4b-B-solvability-200-luna-8k-epoch3NEW

by Stage-org

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

gemma-e4b-3class-sft-v3NEW

by ajujohn8

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

medgemma-4b-it-int4-rtn-w4a16NEW

by Demondiablo

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0image-text-to-text

Imagegemma

conversationallicense:gemma

View on Hugging Face

ppt-pythia-1b-structured-seed3407-stage1NEW

by qing-yao

🖥️ GPUFP16~3 GB1B params

⬇ 0♥ 0text-generation

Language

View on Hugging Face

ppt-pythia-1b-structured-seed3408-stage1NEW

by qing-yao

🖥️ GPUFP16~3 GB1B params

⬇ 0♥ 0text-generation

Language

View on Hugging Face

Gemma-3-12B-itNEW

by RoyYao233

⚡ CPU/GPU~29 GB12B params

⬇ 0♥ 0

Other

View on Hugging Face

ppt-pythia-1b-permuted-seed3408-stage1NEW

by qing-yao

🖥️ GPUFP16~3 GB1B params

⬇ 0♥ 0text-generation

Language

View on Hugging Face

ppt-pythia-1b-permuted-seed3407-stage1NEW

by qing-yao

🖥️ GPUFP16~3 GB1B params

⬇ 0♥ 0text-generation

Language

View on Hugging Face

q3as-8b-ggufNEW

by bladeacer

💻 CPUGGUF~5 GB8B params

⬇ 0♥ 0

Other

View on Hugging Face

moe-ft-006b-s0120NEW

by crazyape777

🖥️ GPUFP16~15 GB6B params

⬇ 0♥ 0

Other

View on Hugging Face

LFM2.5-2.6B-heretic-ExecuTorchNEW

by experimentalmachines

⚡ CPU/GPU~7 GB2.6B params

⬇ 0♥ 0text-generation

Languageother

license:other

View on Hugging Face

gemma2_9b-it-CB_SSFT-asft_gsm8k_lambda1.0_fullft_lr1e-5NEW

by kmseong

🖥️ GPUFP16~22 GB9B params

⬇ 0♥ 0

Other

View on Hugging Face

Apertus-v1.5-8B-text-MLX-mxfp8NEW

by m1rkocasu

💻 CPUMLX~5 GB8B params

⬇ 0♥ 0

Other

View on Hugging Face