nvidia-nemotron-3.5-bolt-74b-a9b-24gb
nvidia-nemotron-3.5-bolt-74b-a9b-24gb is Open weights. Runs on a single 5090 or DGX Spark ๐ฅ. It is ranked #1622 on the Dev Radar, in Other, first seen 15 days ago and shared in 3 posts (16.2k views).
What nvidia-nemotron-3.5-bolt-74b-a9b-24gb says about itself
Image-Text-to-Text model with 22B parameters, built with Transformers. Download, explore files and run it on Hugging Face.
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB ยท Hugging Face Hugging Face Log In Sign Up ","eos_token":"<|im_end|>","pad_token":"<|im_end|>","unk_token":"<unk>"},"chat_template_jinja":"{% macro render_extra_keys(json_dict, handled_keys) %}\n {%- if json_dict is mapping %}\n {%- for json_key in json_dict if json_key not in handled_keys %}\n {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}\n {{- '\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}\n {%- else %}\n {{-'\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_keyโฆ
What people said about nvidia-nemotron-3.5-bolt-74b-a9b-24gb on X
A 74B model in 24GB. @NVIDIAAI just released it on Hugging Face. Nemotron 3.5 Bolt 74B-A9B. 9B active. 256K context. Text, images and video in. It was trained to live in 2 bits, so the whole model fits in 24GB. 24GB is exactly 1 RTX 3090. Nvidia's own numbers against Qwen3.6-35B-A3B: Terminal-Bench 2.1: 51.0 vs 44.4โฆ
โ @superalesha, 15 days ago ยท 135 likes ยท see the post
๐จ @nvidiaai ๐๐จ๐ฆ๐ง ๐ฃ๐จ๐ฆ๐๐๐ ๐ง๐๐ ๐ข๐ก๐-๐ฆ๐ฃ๐๐ฅ๐ ๐๐ฅ๐ข๐ก๐ง๐๐๐ฅ ๐๐ข๐ฅ๐ช๐๐ฅ๐! ๐บ๐ธ๐ฅ ๐ง ๐ก๐๐ ๐ข๐ง๐ฅ๐ข๐ก ๐ฏ.๐ฑ ๐ฆ๐จ๐ฃ๐๐ฅ ๐ฉ๐: 1 MILLION native context tokens + 84.17% SixCat! โก ๐ก๐๐ ๐ข๐ง๐ฅ๐ข๐ก ๐ฏ.๐ฑ ๐๐ข๐๐ง + ๐๐ถ๐๐ถ๐๐ผ๐ฟ๐ฟ ๐๐๐น๐ฎ๐๐ต: 87.8 tok/s single-stream decode + 195.1 tok/s balancedโฆ
โ @ViC305, 14 days ago ยท 72 likes ยท see the post
NVIDIA just dropped Nemotron 3.5 Bolt โก๏ธ ๐ง 74B MoE, only 9B active ๐พ Native 2-bit, the whole model fits in 24GB ๐ 256K context + images & video ๐ Beats Qwen3.6-35B on Terminal-Bench (51 vs 44) and BrowseComp (67 vs 49), per NVIDIA Open weights. Runs on a single 5090 or DGX Spark ๐ฅโฆ
โ @Tech2Wild, 15 days ago ยท 13 likes ยท see the post
Alternatives to nvidia-nemotron-3.5-bolt-74b-a9b-24gb
- Step-5-Preview โ Join the countdown
- Google โ Argon is rolling out today to Google Ultra and Pro subscribers in the @GeminiApp and Search, and Ultra subscribers inโฆ
- nanbeige4.3-33b โ Weโre on a journey to advance and democratize artificial intelligence through open source and open science.
- Spark-X2.5 โ Healthcare-focused AI just got a little lighter. Same powerful reasoning, less memory to worry about. ๐ค
- anymove โ Open source
- Ideogram โ Live in Ideogram and the API
nvidia-nemotron-3.5-bolt-74b-a9b-24gb in numbers
- Rank on the Dev Radar: #1622 of 8801
- Shared in 3 posts by 3 accounts: @superalesha, @ViC305, @Tech2Wild
- 16.2k views on those posts
- First seen 15 days ago, last shared 14 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Other
FAQ
What is nvidia-nemotron-3.5-bolt-74b-a9b-24gb?
Open weights. Runs on a single 5090 or DGX Spark ๐ฅ It was first shared on X 15 days ago and is ranked #1622 on the Dev Radar.
Is nvidia-nemotron-3.5-bolt-74b-a9b-24gb free?
It is open source.
Who shared nvidia-nemotron-3.5-bolt-74b-a9b-24gb?
3 accounts on X, including @superalesha, @ViC305, @Tech2Wild, in 3 posts totalling 16.2k 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. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour โ last update 2026-10-30 21:12 UTC. Full method.