moondream/moondream3-preview
Image-Text-to-Text
•
9B
•
Updated
•
10.5k
•
559
nyuuzyou PRO
nyuuzyou
AI & ML interests
None yet
Recent Activity
liked
a model
about 15 hours ago
moondream/moondream3-preview
liked
a dataset
4 days ago
utter-project/EuroWeb-2512
Organizations
liked
a
model
about 15 hours ago
reacted to
vikhyatk's
post with 🔥
about 15 hours ago
Post
5267
Just released a preview of Moondream 3!
moondream/moondream3-preview
This is a 9B parameter, 2B active MoE VLM with state of the art visual reasoning capabilities.
More details in the release blog post: https://moondream.ai/blog/moondream-3-preview
This is a 9B parameter, 2B active MoE VLM with state of the art visual reasoning capabilities.
More details in the release blog post: https://moondream.ai/blog/moondream-3-preview
- 3 replies
liked
a
dataset
4 days ago
reacted to
mitkox's
post with 👍
6 days ago
Post
4601
I just pushed Claude Code Agent Swarm with 20 coding agents on my desktop GPU workstation.
With local AI, I don’t have /fast CC switch, but I have /absurdlyfast:
- 100’499 tokens/second read, yeah 100k, not a typo | 811 tok/sec generation
- KV cache: 707’200 tokens
- Hardware: 5+ year old GPUs 4xA6K gen1; It’s not the car. It’s the driver.
Qwen3 Coder Next AWQ with cache at BF16. Scores 82.1% in C# on 29-years-in-dev codebase vs Opus 4.5 at only 57.5%. When your codebase predates Stack Overflow, you don't need the biggest model; you need the one that actually remembers Windows 95.
My current bottleneck is my 27" monitor. Can't fit all 20 Theos on screen without squinting.
With local AI, I don’t have /fast CC switch, but I have /absurdlyfast:
- 100’499 tokens/second read, yeah 100k, not a typo | 811 tok/sec generation
- KV cache: 707’200 tokens
- Hardware: 5+ year old GPUs 4xA6K gen1; It’s not the car. It’s the driver.
Qwen3 Coder Next AWQ with cache at BF16. Scores 82.1% in C# on 29-years-in-dev codebase vs Opus 4.5 at only 57.5%. When your codebase predates Stack Overflow, you don't need the biggest model; you need the one that actually remembers Windows 95.
My current bottleneck is my 27" monitor. Can't fit all 20 Theos on screen without squinting.
- 3 replies
[bot] Conversion to Parquet
#1 opened 7 days ago
by
parquet-converter
liked
a
Space
7 days ago
updated
a
model
7 days ago
published
a
model
7 days ago
updated
a
dataset
8 days ago
published
a
dataset
8 days ago
updated
a
Space
8 days ago
published
a
Space
8 days ago
replied to
ZennyKenny's
post
8 days ago
SEO spam has also become a lot less noticeable. I'm hoping that the next step will be to crack down on storage and traffic abuse, and maybe that will mean more generous storage limits.
reacted to
ZennyKenny's
post with 😎
8 days ago
Post
1910
🫠 Brutal! Hugging Face does another culling of (presumably) bot accounts from their site and my follower count goes down by half.
💀 TFW my content and models only appeal to bots. Who’s got the current best AI girlfriend app guys?
💀 TFW my content and models only appeal to bots. Who’s got the current best AI girlfriend app guys?
-
- 8 replies
upvoted
a
changelog
8 days ago
Changelog
Community Evals and Benchmark Repositories
•
48
[bot] Conversion to Parquet
#5 opened 10 days ago
by
parquet-converter
Separate Indian Song Dataset would be helpful too
1
#6 opened 10 days ago
by
Ujjwal-Tyagi
liked
2
models
10 days ago
updated
a
dataset
11 days ago