Show HN: Penny-1.7B Irish Penny Journal style transfer(huggingface.co)

139 points by deepsquirrelnet 1 year ago | 71 comments

LFM2.5 2.6B model competitive with 4x larger models(huggingface.co)

149 points by nateb2022 2 months ago | 39 comments

Qwen3-4B-Thinking-2507(huggingface.co)

151 points by IdealeZahlen 1 year ago | 51 comments

DeepSeek-v4.1-Flash-1017(huggingface.co)

918 points by theykk 9 days ago | 680 comments

Hugging Face model card for DeepSeek-V4.1-Flash-1017, a 763B-parameter MIT-licensed image-text-to-text model from DeepSeek.

Kimi K2.7-Code: open-source coding model with better token efficiency(huggingface.co)

389 points by nekofneko 4 months ago | 208 comments

Hugging Face model card for Moonshot AI's Kimi-K2.7-Code, an open-weights 1T-parameter coding model released under a modified MIT license.

Qwen3.8-2.4T(huggingface.co)

692 points by Philpax 2 months ago | 161 comments

Hugging Face model card for Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter mixture-of-experts text generation model from Qwen in Transformers format.

DeepSeek-v4.1-Flash-1017(huggingface.co)

918 points by theykk 9 days ago | 680 comments

Hugging Face model card for DeepSeek-V4.1-Flash-1017, a 763B-parameter MIT-licensed image-text-to-text model from DeepSeek.

Qwen3.8-2.4T(huggingface.co)

692 points by Philpax 2 months ago | 161 comments

Hugging Face model card for Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter mixture-of-experts text generation model from Qwen in Transformers format.

Llama-3.3-70B-Instruct(huggingface.co)

349 points by pr337h4m 1 year ago | 172 comments

Hugging Face model page for Meta's Llama-3.3-70B-Instruct, a 70B-parameter instruction-tuned text generation model, gated behind a contact-info agreement.

Show HN: TerrainSR – fast, realistic heightmap upscaling model(huggingface.co)

26 points by joegibbs 19 days ago | 7 comments

Hugging Face model card for TerrainSR, a diffusion model that upscales low-resolution terrain heightmaps (100m) to realistic higher-detail elevation data (10m).

Qwen 3.8 27B(huggingface.co)

1391 points by erdaltoprak 2 months ago | 779 comments

Hugging Face model card for Qwen3.8-27B-FP8, an FP8-quantized 27B-parameter image-text-to-text model from Qwen released under Apache 2.0.

GLM-5.3-Flash(z.ai)

1085 points by Philpax 2 months ago | 541 comments

Z.ai blog post announcing GLM-5.3-Flash, a natively multimodal 320B-parameter (18B active) model with hybrid sparse/linear attention, claiming strong coding and agentic results.