Hugging Face's logo

tensorblock
/
Kyro-n1-3B-GGUF

Transformers
GGUF
trl
Reasoning
open-llm
synthetic-data
Deepseek-R1
Qwen2.5
fine-tune
unsloth
Conversational
Agentic
TensorBlock
GGUF
conversational
Model card Files Community
Kyro-n1-3B-GGUF / README.md
morriszms's picture
morriszms
Update README.md
b361466 verified
preview code
|
raw
history blame contribute delete
6.68 kB
metadata
license: other
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
base_model: open-neo/Kyro-n1-3B
library_name: transformers
language:
  - en
  - zh
  - fr
  - es
  - pt
  - de
  - it
  - ru
  - ja
  - ko
  - vi
  - th
  - ar
  - fa
  - he
  - tr
  - cs
  - pl
  - hi
  - bn
  - ur
  - id
  - ms
  - lo
  - my
  - ceb
  - km
  - tl
  - nl
tags:
  - trl
  - Reasoning
  - open-llm
  - synthetic-data
  - Deepseek-R1
  - Qwen2.5
  - fine-tune
  - unsloth
  - Conversational
  - Agentic
  - TensorBlock
  - GGUF
TensorBlock

Website Twitter Discord GitHub Telegram

open-neo/Kyro-n1-3B - GGUF

This repo contains GGUF format model files for open-neo/Kyro-n1-3B.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.

Our projects

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

Model file specification

Filename Quant type File Size Description
Kyro-n1-3B-Q2_K.gguf Q2_K 1.275 GB smallest, significant quality loss - not recommended for most purposes
Kyro-n1-3B-Q3_K_S.gguf Q3_K_S 1.454 GB very small, high quality loss
Kyro-n1-3B-Q3_K_M.gguf Q3_K_M 1.590 GB very small, high quality loss
Kyro-n1-3B-Q3_K_L.gguf Q3_K_L 1.707 GB small, substantial quality loss
Kyro-n1-3B-Q4_0.gguf Q4_0 1.823 GB legacy; small, very high quality loss - prefer using Q3_K_M
Kyro-n1-3B-Q4_K_S.gguf Q4_K_S 1.834 GB small, greater quality loss
Kyro-n1-3B-Q4_K_M.gguf Q4_K_M 1.930 GB medium, balanced quality - recommended
Kyro-n1-3B-Q5_0.gguf Q5_0 2.170 GB legacy; medium, balanced quality - prefer using Q4_K_M
Kyro-n1-3B-Q5_K_S.gguf Q5_K_S 2.170 GB large, low quality loss - recommended
Kyro-n1-3B-Q5_K_M.gguf Q5_K_M 2.225 GB large, very low quality loss - recommended
Kyro-n1-3B-Q6_K.gguf Q6_K 2.538 GB very large, extremely low quality loss
Kyro-n1-3B-Q8_0.gguf Q8_0 3.285 GB very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Kyro-n1-3B-GGUF --include "Kyro-n1-3B-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/Kyro-n1-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'