guangyangmusic/IMSLP-Piano-Scores-leaderboard-results
Preview • Updated • 300 • 1
Anthony A
anthonyya
AI & ML interests
None yet
Recent Activity
liked a dataset about 8 hours ago
guangyangmusic/IMSLP-Piano-Scores-leaderboard-results new activity 2 months ago
gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090:Is the DSpark performance increase solely with SGlang? new activity 3 months ago
unsloth/Qwen3.8-27B-NVFP4:This model's size compared to other NVFP4 modelsOrganizations
None yet
liked a
dataset about 8 hours ago
Is the DSpark performance increase solely with SGlang?
#13 opened 2 months ago
by anthonyya
This model's size compared to other NVFP4 models
2
#24 opened 3 months ago
by anthonyya
NVFP4 Quantization Recipe
👍 1
2
#2 opened 3 months ago
by 
nexus666
liked 5
models 3 months ago
z-lab/Qwen3.8-27B-DFlash2
Text Generation • 2B • Updated • 45.4k • 336
z-lab/Qwen3.8-27B-DFlash2-GGUF
Text Generation • 2B • Updated • 507k • 162
MiniMaxAI/MiniMax-Music3
Text-to-Audio • 2B • Updated • 5.56k • 1.53k
Qwen/Qwen3.8-27B
Image-Text-to-Text • 28B • Updated • 6.96M • • 19.8k
froggeric/Qwen-Fixed-Chat-Templates
Updated • 1.9k
commented on Block Diffusion on Apple Silicon with 3.7× Speedup for Qwopus 3.6 27B 3 months ago
Ignore my previous comment as I was testing the configuration on llama.cpp, which isn't as optimized as MLX based frameworks. However after trying this on mlx-vlm, I'm actually curious how you got this running long enough for your sanity testing. I tried to test it myself, and mlx-vlm is currently suffering from intense RAM spikes (4x the usage) which then very quickly causes OOMs. I opened an issue and I am working with collaborators who confirmed this is an issue.
liked a
model 3 months ago
updated a
model 3 months ago
published a
model 3 months ago
updated a
model 3 months ago
published a
model 3 months ago
updated a
model 3 months ago
published a
model 3 months ago
Are quants required to match?
#1 opened 3 months ago
by anthonyya
commented on Block Diffusion on Apple Silicon with 3.7× Speedup for Qwopus 3.6 27B 3 months ago
Can you run this on a real benchmark? I tested this on my M4 Max with a real coding benchmark and I'm not seeing anything close to your 55 tok/s, I'm getting around 20.
liked a
model 4 months ago
