bespoke-nimble-9b
bespoke-nimble-9b is We’re on a journey to advance and democratize artificial intelligence through open source and open science.. It is ranked #33 on the AI Radar, in Open & local models, first seen 23 h ago and shared in 5 posts (372.1k views).
bespokelabs/Bespoke-Nimble-9B · Hugging Face Hugging Face Log In Sign Up ","pad_token":"<|endoftext|>","unk_token":null},"chat_template_jinja":"{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if…
What people said about bespoke-nimble-9b on X
Introducing Bespoke Nimble: an open data, open model, open recipe for an open Jev. Code and info: https://github.com/bespokelabsai/nimble Model: https://huggingface.co/bespokelabs/Bespoke-Nimble-9B Data: * A new data curation recipe called contrastive data curation. * Slightly change facts to generate negative data.…
— @madiator, 23 h ago · 1k likes · see the post
牛逼！Jev 刚火没两天，已经有人搞了个开源的Jev🤣 @bespokelabsai 发布了一个开源版的Jev：Bespoke Nimble。 更离谱的是，整个项目是基于 Qwen3.5-9B ，只花了大约两天。 数据、模型权重、训练配方、推理代码全部公开，而且没有从 Jev 蒸馏，只拿 Jev 做评测参照。 最终方法是在 Qwen3.5-9B 上做了一次很轻量的 LoRA微调。 只用了2676 条训练数据，结果在他们自己的 324 条 held-out 测试集上拿到了90.12%，而原版的Jev是93.21%。 一个 9B 模型，已经做到距离 Jev 只差 3 个百分点。…
— @MaxForAI, 8 h ago · 322 likes · see the post
We lost our CEO for 2 days and then he came back with this awesome 9B model.
— @AlexGDimakis, 14 h ago · 308 likes · see the post
Alternatives to bespoke-nimble-9b
- Pirate Face — The un-bannable, checksum-verified mirror for open models. Claim your handle before a squatter does.
- atomic.chat — Run AI models locally ->
- deepseek-v4.1-flash-exl3-2x-dgx-sparks — DeepSeek v4.1 Flash EXL3 2.9 bpw for 2x DGX Sparks - MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks
- Cactus Compute — It runs on mobiles, wearables, smart home devices, small robots and microcontrollers, with prebuilt engines for macOS,…
- orcabonsai-27b-uncensored — Open source
- deepseek-v4.1-flash — Original safetensors
bespoke-nimble-9b in numbers
- Rank on the AI Radar: #33 of 1181
- Shared in 5 posts by 5 accounts: @madiator, @MaxForAI, @AlexGDimakis, @krishnanrohit
- 372.1k views on those posts
- First seen 23 h ago, last shared 5 h ago
- Pricing seen by Jev: open source
- Market: Open & local models
FAQ
What is bespoke-nimble-9b?
We’re on a journey to advance and democratize artificial intelligence through open source and open science. It was first shared on X 23 h ago and is ranked #33 on the AI Radar.
Is bespoke-nimble-9b free?
It is open source.
Who shared bespoke-nimble-9b?
5 accounts on X, including @madiator, @MaxForAI, @AlexGDimakis, in 5 posts totalling 372.1k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 16:11 UTC. Full method.