Myric/Llama-4-Scout-17B-16E-Instruct-APEX-GGUF
Text Generation • 108B • Updated • 707 • 1
Bryan Harris
Myric
AI & ML interests
I'm interested in running models on hardware I have rather than hardware I can rent (Or maybe in addition to hardware I can rent.)
Recent Activity
updated a model about 9 hours ago
Myric/Llama-4-Scout-17B-16E-Instruct-APEX-GGUF updated a model about 9 hours ago
Myric/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-APEX-GGUF updated a model about 9 hours ago
Myric/Qwen3.5-35B-A3B-APEX-GGUFOrganizations
None yet
updated 3
models about 9 hours ago
Why Q3_K for ssm.apha/beta?
2
#2 opened 2 days ago
by 
anjeysapkovski
published a
model 4 days ago
updated a
model 4 days ago
updated 2
models 6 days ago
reacted to maglun's post with ❤️ 6 days ago
Post
2939
Inspect model quantization in the browser, without download
Curious how models on Hugging Face spend their "bit budget"? A few days ago I shared the first version of a little tool I built out of my own curiosity (and for fun). Since then, thanks in large part to great feedback from people here, a lot has changed.
New in the last few days:
- GGUF support - handy with all the new great GGUF quants
- Decode for AWQ, GPTQ, NF4, mxfp4 packed experts, packed-int32, and additive-codebook formats
- Improved comparison view for diffing two quants of the same model
- Built-in anonymous report-issue button connecting a report to specific model
- plus many small fixes
After my first post I got great feedback from several community members, and some issues were fixed within hours. I'm planning an acknowledgments section on the site, and when you report an issue you get a receipt ID you can keep to claim credit later. (reports are anonymous by design; I store no identity, so the receipt hash works like a bearer token for your find)
It's still very much a side project I hope others find useful. Explore any HF model in the browser without downloading it, the webpage reads from the safetensors header via a range request, and only tensors you click stream, and large ones are sampled, not downloaded in full. And there is a report button right in the tool when things don’t look right.
Feedback very welcome, especially models that break it :) Or ideas on what is missing.
https://tensorlens.dev
(screenshot attached from viewing one of Unsloth's GGUF quants)
Curious how models on Hugging Face spend their "bit budget"? A few days ago I shared the first version of a little tool I built out of my own curiosity (and for fun). Since then, thanks in large part to great feedback from people here, a lot has changed.
New in the last few days:
- GGUF support - handy with all the new great GGUF quants
- Decode for AWQ, GPTQ, NF4, mxfp4 packed experts, packed-int32, and additive-codebook formats
- Improved comparison view for diffing two quants of the same model
- Built-in anonymous report-issue button connecting a report to specific model
- plus many small fixes
After my first post I got great feedback from several community members, and some issues were fixed within hours. I'm planning an acknowledgments section on the site, and when you report an issue you get a receipt ID you can keep to claim credit later. (reports are anonymous by design; I store no identity, so the receipt hash works like a bearer token for your find)
It's still very much a side project I hope others find useful. Explore any HF model in the browser without downloading it, the webpage reads from the safetensors header via a range request, and only tensors you click stream, and large ones are sampled, not downloaded in full. And there is a report button right in the tool when things don’t look right.
Feedback very welcome, especially models that break it :) Or ideas on what is missing.
https://tensorlens.dev
(screenshot attached from viewing one of Unsloth's GGUF quants)
- 3 replies
updated a
model 6 days ago
published a
model 6 days ago
reacted to appvoid's post with 🔥 6 days ago
Post
1953
Random corporate secret of tonight:
Try overfitting a tiny model on billions of high-quality datapoints: you can't. You can do 100 epochs and see the model still improving.
You're welcome.
Try overfitting a tiny model on billions of high-quality datapoints: you can't. You can do 100 epochs and see the model still improving.
You're welcome.
- 1 reply
Lightning is really efficient
#1 opened 7 days ago
by Myric
Quants wrong?
5
#2 opened 8 days ago
by 
CNWPlayer
published a
model 7 days ago
updated a
model 7 days ago
updated a
model 8 days ago
pytorch imatrix
1
#2 opened 9 days ago
by 
rahul7star
Coding benchmark: APEX-i-quality avoided thinking loops
3
#7 opened 10 days ago
by 
LantaldeMikel
Error on loading I-Quality model
2
#1 opened 12 days ago
by 
Emerald7664