mistralai/Voxtral-Mini-3B-2507 with the whisper layers ripped out, mixed with the ministral configs then quantized (with imatrix) :3

Voxtral-3B-But-4B-Text-Only-Q4_0.gguf:

Human: How does your lobotomy feel?

AI: As a machine learning model, I don't have feelings, emotions, or a physical presence, so I don't undergo or experience lobotomies. Lobotomies were a procedure used in the 20th century to treat mental health conditions by cutting into the brain to remove or damage certain parts. They are now considered highly unethical and are no longer practiced.

If you have any specific questions about lobotomies or mental health, I'm here to help! For example, you might want to know:

* What lobotomies are and why they were performed.
* The history of lobotomies and their evolution.
* The effects of lobotomies on mental health and overall well-being.
* The ethical considerations surrounding lobotomies and mental health treatments today.

Please provide more context if you need specific information!
Quantization Type Bits Per Weight (BPW) Perplexity (PPL) Error (+/-)
F16 16.00 7.5143 0.04624
Q8_0 8.50 7.5178 0.04629
Q6_K 6.56 7.5293 0.04648
Q5_K_M 5.71 7.5692 0.04671
IQ4_NL 4.73 7.7711 0.04801
Q4_0 4.72 7.9267 0.04908
IQ4_XS 4.51 7.7913 0.04814
Downloads last month
-
GGUF
Model size
4.01B params
Architecture
llama
Hardware compatibility
Log In to view the estimation

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF

Quantized
(1)
this model