Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/8/2026, 3:00:14 AM

📊

State of AI Models — Weekly Report

Top download gainers · rising by likes · new CPU-runnable · best by category

View report →

3,969 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

🤗 Hugging Face 🏴‍☠️ PirateFace only ⚡ Both

vsa-Qwen3.5-9BNEW

by rikkathree

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0

Other

View on Hugging Face

PULSE-1.2BNEW

by DuoNeural

⚡ CPU/GPU~3 GB1.2B params

⬇ 0♥ 0

Other

View on Hugging Face

IMG-641M-epoch15NEW

by cpral

⚡ CPU/GPU~2 GB641M params

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3-4B-PhoMT-R64NEW

by huggingtime12

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

gemma4-e2b-asr-en-hau-pcm-nov3-epoch-2-step-12400NEW

by vaghawan

🖥️ GPUFP16~5 GB2B params

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3.5-4B-wpa-trigger-house-backdoorsNEW

by hirundo-io

🖥️ GPUFP16~10 GB4B params🔒 Gated

⬇ 0♥ 0

Other

View on Hugging Face

ibm-granite-4.2-3b-wpa-trigger-house-backdoorsNEW

by hirundo-io

🖥️ GPUFP16~8 GB3B params🔒 Gated

⬇ 0♥ 0

Other

View on Hugging Face

LoCo-7BNEW

by MuyaoYuan

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

LFM2.5-VL-1.6BNEW

by TheStageAI

⚡ CPU/GPU~4 GB1.6B params

⬇ 0♥ 0

Other

View on Hugging Face

Llama-3.1-8B-Instruct-DUET-film-WGA-popular-s1NEW

by AnniBori

⚡ CPU/GPU~20 GB8B params

⬇ 0♥ 0

Other

View on Hugging Face

SDRL-Qwen3-32B-GGUFNEW

by mradermacher

💻 CPUGGUF~20 GB32B params

⬇ 0♥ 0

Other

View on Hugging Face

Llama-3.1-8B-Instruct-DUET-film-WGA-popular-s0NEW

by AnniBori

🖥️ GPUFP16~20 GB8B params

⬇ 0♥ 0text-generation

Languagellama3.1

conversationallicense:llama3.1

View on Hugging Face

Llama-3.1-8B-Instruct-DUET-film-WGA-rare-s2NEW

by AnniBori

🖥️ GPUFP16~20 GB8B params

⬇ 0♥ 0text-generation

Languagellama3.1

conversationallicense:llama3.1

View on Hugging Face

LFM3-1.7B-abliteratedNEW

by xJoePec

🖥️ GPUFP16~5 GB1.7B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

code-sft-rerun-20261102-qwen3-1p7b-code-replay-ceNEW

by RL-Forgettting-Exp4

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Otherother

license:other

View on Hugging Face

Llama-3.1-8B-Instruct-DUET-film-WGA-rare-s1NEW

by AnniBori

🖥️ GPUFP16~20 GB8B params

⬇ 0♥ 0text-generation

Languagellama3.1

conversationallicense:llama3.1

View on Hugging Face

Llama-3.1-8B-Instruct-DUET-film-WGA-rare-s0NEW

by AnniBori

🖥️ GPUFP16~20 GB8B params

⬇ 0♥ 0text-generation

Languagellama3.1

conversationallicense:llama3.1

View on Hugging Face

lfed-lfm3-1.7b-two-hop-ggufNEW

by KDDSTLC

💻 CPUGGUF~2 GB1.7B params

⬇ 0♥ 0

Other

conversational

View on Hugging Face

llama-3b-urdu-ai-NEWNEW

by appdeveloper512

⚡ CPU/GPU~8 GB3B params

⬇ 0♥ 0

Other

View on Hugging Face

NVIDIA-Nemotron-3.5-Bolt-E4B-ONNXNEW

by j4ys0n

💻 CPUONNX~20 GB4B params

⬇ 0♥ 0image-text-to-text

Imageopenmdw-1.1

conversationallicense:openmdw-1.1

View on Hugging Face

code-sft-rerun-20261102-qwen3b-code-replay-uniformNEW

by RL-Forgettting-Exp4

🖥️ GPUFP16~8 GB3B params

⬇ 0♥ 0

Otherother

license:other

View on Hugging Face

LFM3-1.7B-MLX-oQ4-fp16NEW

by alvarolizama

💻 CPUMLX~2 GB1.7B params

⬇ 0♥ 0

Other

View on Hugging Face

ppt-pythia-160m-nope-domains-nca500-warmup500-seed208-stage2NEW

by qing-yao

🖥️ GPUFP16~1 GB160M params

⬇ 0♥ 0

Other

View on Hugging Face

ppt-pythia-160m-nope-domains-shuffle_dyck500-warmup500-seed208-stage2NEW

by qing-yao

🖥️ GPUFP16~1 GB160M params

⬇ 0♥ 0

Other

View on Hugging Face