You can deploy this model and start earning money today!

tensorblock/
Vikhr-7B-instruct_0.4-GGUF

Name: Vikhr-7B-instruct_0.4-GGUF
Availability: InStock

Views

No views yet

Vikhrmodels/Vikhr-7B-instruct_0.4 - GGUF

This repo contains GGUF format model files for Vikhrmodels/Vikhr-7B-instruct_0.4.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Forge
Forge Project
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
MCP Servers	Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

<s><|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Filename	Quant type	File Size	Description
Vikhr-7B-instruct_0.4-Q2_K.gguf	Q2_K	2.740 GB	smallest, significant quality loss - not recommended for most purposes
Vikhr-7B-instruct_0.4-Q3_K_S.gguf	Q3_K_S	3.173 GB	very small, high quality loss
Vikhr-7B-instruct_0.4-Q3_K_M.gguf	Q3_K_M	3.503 GB	very small, high quality loss
Vikhr-7B-instruct_0.4-Q3_K_L.gguf	Q3_K_L	3.785 GB	small, substantial quality loss
Vikhr-7B-instruct_0.4-Q4_0.gguf	Q4_0	4.077 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Vikhr-7B-instruct_0.4-Q4_K_S.gguf	Q4_K_S	4.106 GB	small, greater quality loss
Vikhr-7B-instruct_0.4-Q4_K_M.gguf	Q4_K_M	4.318 GB	medium, balanced quality - recommended
Vikhr-7B-instruct_0.4-Q5_0.gguf	Q5_0	4.927 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Vikhr-7B-instruct_0.4-Q5_K_S.gguf	Q5_K_S	4.927 GB	large, low quality loss - recommended
Vikhr-7B-instruct_0.4-Q5_K_M.gguf	Q5_K_M	5.051 GB	large, very low quality loss - recommended
Vikhr-7B-instruct_0.4-Q6_K.gguf	Q6_K	5.830 GB	very large, extremely low quality loss
Vikhr-7B-instruct_0.4-Q8_0.gguf	Q8_0	7.550 GB	very large, extremely low quality loss - not recommended

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Vikhr-7B-instruct_0.4-GGUF --include "Vikhr-7B-instruct_0.4-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Vikhr-7B-instruct_0.4-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'