kimi-k3-pruned75
kimi-k3-pruned75 is Image-Text-to-Text model with 737B parameters. Download, explore files and run it on Hugging Face.. It is ranked #475 on the Dev Radar, in Other, first seen 1 h ago and shared in 1 post (910 views).
mgoin/Kimi-K3-pruned75 · Hugging Face Hugging Face Log In Sign Up mgoin / Kimi-K3-pruned75 Like 2 Image-Text-to-Text Transformers Safetensors kimi_k3 feature-extraction kimi-k3 mixture-of-experts pruning vllm custom_code Eval Results (legacy) 8-bit precision License: kimi-k3 Model card Files Files and versions xet Community Deploy Copy to bucket Use this model Kimi-K3-pruned75 This is a calibration-free, safetensors-only expert-pruned checkpoint derived from moonshotai/Kimi-K3 . It removes 75% of the routed experts and is intended for vLLM serving and evaluation smoke tests while accurate calibration-based pruning, such as REAP support in…
What people said about kimi-k3-pruned75 on X
😳震惊！vLLM直接砍掉Kimi K3.1 Pro 75%专家，体积暴降到476GB！ 2.8万亿参数的超大MoE模型，被粗暴剪到只剩约700-750B参数，模型文件直接压到476GB，原始每层896个专家只保留224个，砍掉75%，属于校准无关的实验性剪枝，专门用来做vLLM服务和性能测试。 核心亮点： 🔹参数从2.8T暴降到约700-750B，体积只剩476GB 🔹每层专家：896 → 224（保留25%） 🔹定位是烟雾测试/性能调优，不是能正常用的模型 🔹GSM8K准确率从原版约95.5%直接掉到34.4%，质量回退非常明显 🔹官方明确说输出基本不可用，只适合跑服务和基准 使用步骤：…
— @NFT_Chen, 1 h ago · 16 likes · see the post
Alternatives to kimi-k3-pruned75
- modelscope.ai — 📄 Paper
- deepseek-v4.1-flash-1017-gguf — Image-Text-to-Text model with 748B parameters. Download, explore files and run it on Hugging Face.
- deepseek-v4.1-flash-1017-uncensored-gsq-rco-gguf — Text Generation model with 552B parameters. Download, explore files and run it on Hugging Face.
- qwen3.8-flash-next-gguf — Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
- hermes-voice — the code, the setup skill and the "hey hermes" wake word
- imagination-studio-by-keys-wasserman — @samael_voolt @SamJWasserman @ComfyUI @robinjhuang @hellorob
kimi-k3-pruned75 in numbers
- Rank on the Dev Radar: #475 of 9420
- Shared in 1 post by 1 account: @NFT_Chen
- 910 views on those posts
- First seen 1 h ago, last shared 1 h ago
- Pricing seen by AGK Intelligence: not stated
- Market: Other
FAQ
What is kimi-k3-pruned75?
Image-Text-to-Text model with 737B parameters. Download, explore files and run it on Hugging Face. It was first shared on X 1 h ago and is ranked #475 on the Dev Radar.
Is kimi-k3-pruned75 free?
Pricing is not stated on the page we read.
Who shared kimi-k3-pruned75?
1 account on X, including @NFT_Chen, in 1 post totalling 910 views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.8k posts from 5k X accounts over the last 21 days, 9.4k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 23:22 UTC. Full method.