Menlo Research Quantizations
Ben Shankles PRO
warshanks
AI & ML interests
MLX, AWQ, GPTQ
Recent Activity
new activity
about 23 hours ago
mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit:Convert in bf16 or fp16?
upvoted
a
changelog
about 24 hours ago
Introducing HF Jobs: Run scalable compute jobs on Hugging Face
updated
a model
2 days ago
warshanks/bernie0.1-AWQ
Organizations
W4A16 quants made with llmcompressor
-
warshanks/Qwen3-8B-abliterated-AWQ
Text Generation • 2B • Updated • 123 -
warshanks/Qwen3-4B-abliterated-AWQ
Text Generation • 1B • Updated • 56 -
warshanks/Qwen3-1.7B-abliterated-AWQ
Text Generation • 0.8B • Updated • 19 -
warshanks/Josiefied-Qwen3-4B-abliterated-v2-AWQ
Text Generation • 1B • Updated • 36
Menlo Research Quantizations
W4A16 quants made with llmcompressor
-
warshanks/Qwen3-8B-abliterated-AWQ
Text Generation • 2B • Updated • 123 -
warshanks/Qwen3-4B-abliterated-AWQ
Text Generation • 1B • Updated • 56 -
warshanks/Qwen3-1.7B-abliterated-AWQ
Text Generation • 0.8B • Updated • 19 -
warshanks/Josiefied-Qwen3-4B-abliterated-v2-AWQ
Text Generation • 1B • Updated • 36
spaces
7
pinned
Running
on
Zero
1
MedGemma 27B IT
🩻
Chat with MedGemma 27B, a medical variant of Gemma 3
pinned
Running
on
Zero
23
MedGemma 4B IT
🩻
Chat with MedGemma 4B, a medical variant of Gemma 3
pinned
Running
on
Zero
8
Lingshu 7B
🩻
Chat with Lingshu 7B, a multimodal medical model
pinned
Running
on
Zero
3
Lingshu 32B
🩻
Chat with Lingshu 32B, a multimodal medical model
Running
on
Zero
FLUX.1 [dev]
🖥
Generate images from text prompts
Running
Seinfeld
☕
Chat with Seinfeld powered by Gemini
models
13
warshanks/bernie0.1-AWQ
1B
•
Updated
•
9
warshanks/Qwen3-8B-abliterated-AWQ
Text Generation
•
2B
•
Updated
•
123
warshanks/Qwen3-1.7B-abliterated-AWQ
Text Generation
•
0.8B
•
Updated
•
19
warshanks/Lucy-AWQ
Text Generation
•
0.8B
•
Updated
•
18
warshanks/Lucy-128k-AWQ
Text Generation
•
0.8B
•
Updated
•
81
warshanks/Dolphin-Mistral-24B-Venice-Edition-AWQ
4B
•
Updated
•
24
warshanks/Voxtral-Mini-3B-2507-FP8
Audio-Text-to-Text
•
Updated
•
19
warshanks/Jan-nano-128k-AWQ
Text Generation
•
1B
•
Updated
•
54
warshanks/Jan-nano-AWQ
Text Generation
•
1B
•
Updated
•
55
•
2
warshanks/Qwen3-4B-abliterated-AWQ
Text Generation
•
1B
•
Updated
•
56
datasets
0
None public yet