Mistral-7B-Instruct-v0.2 — GGUF (Q4_K_M)
TheBloke's Q4_K_M GGUF, re-hosted with measured performance for the 1bit engine on Strix Halo.
Contents
mistral-7b-instruct-v0.2.Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 1192 tok/s · tg128: 38.0 tok/s
Running it
1bit serve -m mistral-7b-instruct-v0.2.Q4_K_M.gguf --device vulkan
Attribution
- Model: mistralai/Mistral-7B-Instruct-v0.2, Apache 2.0.
- Quantization: TheBloke/Mistral-7B-Instruct-v0.2-GGUF.
- License: Apache 2.0, inherited from the base model.
- Downloads last month
- 78
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for 1bit-MONSTER/Mistral-7B-Instruct-v0.2-GGUF
Base model
mistralai/Mistral-7B-Instruct-v0.2