oh nice! well, good luck. very excited.
alkinun
AtAndDev
AI & ML interests
decentralize
Recent Activity
repliedto Banaxi-Tech's post about 6 hours ago
We're excited to release BananaMind 2.5 Pro.
It's done some post-training on our BananaMind 2 Pro base, via distillation of SmolLM2 360M.
It scores 28.98 INT INDEX compared to 24.96 of BananaMind 2 Pro on the https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard
Check it out at https://huggingface.co/BananaMind/BananaMind-2.5-Pro
https://huggingface.co/BananaMind
@ArushCodes
@Bc-AI repliedto Banaxi-Tech's post about 7 hours ago
We're excited to release BananaMind 2.5 Pro.
It's done some post-training on our BananaMind 2 Pro base, via distillation of SmolLM2 360M.
It scores 28.98 INT INDEX compared to 24.96 of BananaMind 2 Pro on the https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard
Check it out at https://huggingface.co/BananaMind/BananaMind-2.5-Pro
https://huggingface.co/BananaMind
@ArushCodes
@Bc-AI reacted to Banaxi-Tech's post with 🔥 about 7 hours ago
We're excited to release BananaMind 2.5 Pro.
It's done some post-training on our BananaMind 2 Pro base, via distillation of SmolLM2 360M.
It scores 28.98 INT INDEX compared to 24.96 of BananaMind 2 Pro on the https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard
Check it out at https://huggingface.co/BananaMind/BananaMind-2.5-Pro
https://huggingface.co/BananaMind
@ArushCodes
@Bc-AI Organizations
replied to Banaxi-Tech's post about 6 hours ago
replied to Banaxi-Tech's post about 7 hours ago
cool, but what happened to the promise? :)
reacted to Banaxi-Tech's post with 🔥 about 7 hours ago
Post
3,041
We're excited to release BananaMind 2.5 Pro.
It's done some post-training on our BananaMind 2 Pro base, via distillation of SmolLM2 360M.
It scores 28.98 INT INDEX compared to 24.96 of BananaMind 2 Pro on the AxiomicLabs/Open_SLM_Leaderboard
Check it out at BananaMind/BananaMind-2.5-Pro
BananaMind
@ArushCodes
@Bc-AI
It's done some post-training on our BananaMind 2 Pro base, via distillation of SmolLM2 360M.
It scores 28.98 INT INDEX compared to 24.96 of BananaMind 2 Pro on the AxiomicLabs/Open_SLM_Leaderboard
Check it out at BananaMind/BananaMind-2.5-Pro
@ArushCodes
@Bc-AI
- 21 replies
liked a
model about 8 hours ago
reacted to savoji's post with 🔥 1 day ago
Post
2,382
Idol, a new Apache-2.0 image-to-3D model from @speridlabs , makes a 3D Gaussian splat from one image in 7.2 GB of peak VRAM. It is the #1 trending model on the Hub with 1,057 likes.
It writes a standard 3DGS .ply with up to 1,048,576 Gaussians, including sides the picture never showed, and does background removal and framing itself. The catch: the only quality evidence is the authors' own benchmark, on a repo created 2026-10-28.
📊 The numbers
• Authors' benchmark, 1 x H100: best in 6 of 8 columns vs TripoSplat, TRELLIS and LGM (SSIM 0.726, LPIPS 0.213, DINOv2 0.781, CLIP 0.885)
• LGM wins PSNR (12.46 vs 12.25) and speed (1.1 s). Idol takes 6.8 s vs 7.1 s for TRELLIS and 9.9 s for TripoSplat
• 262,144 Gaussians, 50 steps: 3.4 s on B300, 6.7 s on H100, 19.1 s on RTX 4090, 46.2 s on a 10 GB RTX 3080
🛠️ Try it
• Install idol-sdk, accept the terms of the gated DINOv3 and FLUX.2-dev models, run hf auth login
• python -m idol.sample --image photo.jpg --mode real
• --num_gaussians runs from 32,768 (0.4 MB) to 1,048,576 (12.2 MB)
⚠️ Caveats
• Test set and size are not named, and no independent evaluation exists yet
• The card says "under 2 seconds", but the timing table shows 3.4 s at best
• Single objects only, NVIDIA CUDA required, no failure cases shown
speridlabs/idol
https://speridlabs.com/research/idol
If you run it on your own messy photos, how do the unseen sides hold up?
📚 Read it elsewhere
• The deep dive on Medium: https://medium.com/p/5f660ae6ae56
• The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/speridlabs-idol-builds-3d-splats
• The thread on X: https://x.com/saavoji/status/2119137739580858545
• Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#speridlabs-idol
It writes a standard 3DGS .ply with up to 1,048,576 Gaussians, including sides the picture never showed, and does background removal and framing itself. The catch: the only quality evidence is the authors' own benchmark, on a repo created 2026-10-28.
📊 The numbers
• Authors' benchmark, 1 x H100: best in 6 of 8 columns vs TripoSplat, TRELLIS and LGM (SSIM 0.726, LPIPS 0.213, DINOv2 0.781, CLIP 0.885)
• LGM wins PSNR (12.46 vs 12.25) and speed (1.1 s). Idol takes 6.8 s vs 7.1 s for TRELLIS and 9.9 s for TripoSplat
• 262,144 Gaussians, 50 steps: 3.4 s on B300, 6.7 s on H100, 19.1 s on RTX 4090, 46.2 s on a 10 GB RTX 3080
🛠️ Try it
• Install idol-sdk, accept the terms of the gated DINOv3 and FLUX.2-dev models, run hf auth login
• python -m idol.sample --image photo.jpg --mode real
• --num_gaussians runs from 32,768 (0.4 MB) to 1,048,576 (12.2 MB)
⚠️ Caveats
• Test set and size are not named, and no independent evaluation exists yet
• The card says "under 2 seconds", but the timing table shows 3.4 s at best
• Single objects only, NVIDIA CUDA required, no failure cases shown
speridlabs/idol
https://speridlabs.com/research/idol
If you run it on your own messy photos, how do the unseen sides hold up?
📚 Read it elsewhere
• The deep dive on Medium: https://medium.com/p/5f660ae6ae56
• The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/speridlabs-idol-builds-3d-splats
• The thread on X: https://x.com/saavoji/status/2119137739580858545
• Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#speridlabs-idol
- 4 replies
liked a
Space 1 day ago
liked 2
datasets 1 day ago
liked 7
models 1 day ago
klein-ml/Klein-TTS-X1.5-Pro
Text-to-Speech • 13.1M • Updated • 169 • 9
unsloth/gemma-3n-E4B-it-GGUF
Image-Text-to-Text • 7B • Updated • 46.7k • 209
unsloth/gemma-3-1b-it
Text Generation • 1.0B • Updated • 51.5k • • 23
unsloth/orpheus-3b-0.1-ft
Text-to-Speech • 3B • Updated • 44.5k • 17
unsloth/gemma-3n-E2B-it-GGUF
Image-Text-to-Text • 4B • Updated • 44.5k • 64
unsloth/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF
Image-Text-to-Text • 2B • Updated • 47.5k • 67
unsloth/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 62k • 13
reacted to danielhanchen's post with ❤️🚀🔥 1 day ago
Post
4,932
Qwen3.8-Flash-Next GGUFs now run faster with less thinking and less token use.
Unsloth Dynamic V3.1 GGUFs bring thinking & token use to match 95% of full precision Qwen3.8-Flash.
Results: 50% fewer tokens + 15% higher accuracy vs same size quants.
GGUF: unsloth/Qwen3.8-Flash-Next-GGUF
Analysis/Guide: https://unsloth.ai/docs/models/qwen3.8-next
Unsloth Dynamic V3.1 GGUFs bring thinking & token use to match 95% of full precision Qwen3.8-Flash.
Results: 50% fewer tokens + 15% higher accuracy vs same size quants.
GGUF: unsloth/Qwen3.8-Flash-Next-GGUF
Analysis/Guide: https://unsloth.ai/docs/models/qwen3.8-next
- 3 replies
We did it! Qwen3.8-27B is now the #1 most liked GGUF of all time! 🎉
👍🔥 56
2
#127 opened 2 months ago
by 
danielhanchen
liked a
model 2 days ago