YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
q5_k_m version of HyperbeeAI/Tulpar-7b-v2. Designed to be processed further and used in local llm applications
q5_k_m means Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, otherwise Q5_K
good mix of performance and speed.
please note this is for PC. Mobile version with lower precision will be out soon.
- Downloads last month
- 2
Hardware compatibility
Log In
to view the estimation
4-bit
5-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support