Qiang

mikv39

·

AI & ML interests

LLM/TTS/ASR/Infer

Recent Activity

reacted to danielhanchen's post with 🔥 about 22 hours ago

We’re releasing new Qwen3.8-Flash-Next GGUFs with 15% higher accuracy. Unsloth Dynamic V3.1 outperforms others by >15% on Terminal Bench, DeepSWE & more benchmarks (256K context). Run on 32GB+ RAM setups. GGUF: https://huggingface.co/unsloth/Qwen3.8-Flash-Next-GGUF Blog: https://unsloth.ai/docs/models/qwen3.8-next

liked a model 2 days ago

mikv39/gpt-sovits-onnx-custom

liked a model 2 days ago

moonshotai/Kimi-K3.1-Pro

View all activity

Organizations

reacted to danielhanchen's post with 🔥 about 22 hours ago

Post

5,987

We’re releasing new Qwen3.8-Flash-Next GGUFs with 15% higher accuracy.

Unsloth Dynamic V3.1 outperforms others by >15% on Terminal Bench, DeepSWE & more benchmarks (256K context).

Run on 32GB+ RAM setups.

GGUF: unsloth/Qwen3.8-Flash-Next-GGUF
Blog: https://unsloth.ai/docs/models/qwen3.8-next

liked 2 models 2 days ago

mikv39/gpt-sovits-onnx-custom

Text-to-Speech • Updated Oct 4 • 2

moonshotai/Kimi-K3.1-Pro

Image-Text-to-Text • 2.8T • Updated 1 day ago • 18.4k • • 1.39k

liked a model 11 days ago

tencent/Hy-Nomas

Updated 1 day ago • 83.5k • 147

liked 3 models 16 days ago

OpenMOSS-Team/MOSS-SoundEffect-v2.0

Text-to-Audio • 1B • Updated May 26 • 5.24k • 156

audio-cpp/MiniMax-Music3-GGUF

Text-to-Audio • 25.2M • Updated Oct 6 • 676k • 43

stabilityai/stable-audio-3-medium

Text-to-Audio • 2B • Updated about 1 month ago • 93.2k • • 564

liked a model 17 days ago

inclusionAI/Ming-3.0-tts-0.5B

Text-to-Speech • 1B • Updated 10 days ago • 12k • 212

upvoted a collection 18 days ago

Ming-3.0

5 items • Updated 10 days ago • 21

liked a model 28 days ago

Qwen/Qwen-Image-2.1-Turbo

Text-to-Image • 7B • Updated 25 days ago • 46.2k • 1.12k

liked a model about 1 month ago

google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 9 days ago • 483k • 3.17k

updated a model about 1 month ago

mikv39/gpt-sovits-onnx-custom

Text-to-Speech • Updated Oct 4 • 2

published a model about 1 month ago

mikv39/gpt-sovits-onnx-custom

Text-to-Speech • Updated Oct 4 • 2

upvoted a collection about 1 month ago

FLUX 3 Action

Open weights 7B world action model: base and shared encoders, SO-101 and DROID policies. Code: https://github.com/black-forest-labs/flux-action • 3 items • Updated Oct 2 • 47

liked 6 models about 2 months ago

XiaomiMiMo/MiMo-V2.6-Flash-RL

Text Generation • 311B • Updated 9 days ago • 76.2k • • 587

stepfun-ai/Step-5-Preview-BF16

604B • Updated 23 days ago • 1.41k • 55

FastVideo/FastVideo-FastH3-Comfy

Updated Sep 16 • 615k • 167

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated Jun 12 • 221k • 3.17k

m-a-p/YuE2-3B

Text-to-Audio • 4B • Updated Oct 6 • 23.2k • 1.24k

deepseek-ai/DeepSeek-V4.1-Flash

Image-Text-to-Text • 763B • Updated 21 days ago • 1.88M • • 4.88k