Instructions to use zenlm/zen5-flash-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zenlm/zen5-flash-gguf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zenlm/zen5-flash-gguf")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("zenlm/zen5-flash-gguf") model = AutoModelForCausalLM.from_pretrained("zenlm/zen5-flash-gguf") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use zenlm/zen5-flash-gguf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zenlm/zen5-flash-gguf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zenlm/zen5-flash-gguf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zenlm/zen5-flash-gguf
- SGLang
How to use zenlm/zen5-flash-gguf with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "zenlm/zen5-flash-gguf" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zenlm/zen5-flash-gguf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "zenlm/zen5-flash-gguf" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zenlm/zen5-flash-gguf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zenlm/zen5-flash-gguf with Docker Model Runner:
docker model run hf.co/zenlm/zen5-flash-gguf
Zen5 Flash
Smallest and fastest tier in the Zen5 family. A dense 4B-parameter instruct model with sub-100ms time-to-first-token at 32K context, tuned for high-throughput routing and simple agent loops.
Repackaged from Qwen/Qwen3-4B (apache-2.0, Alibaba Qwen) โ redistributed as safetensors from the abliterated huihui-ai/Qwen3-4B-abliterated variant. Not trained from scratch โ a permissively-licensed redistribution for the OSS-clean Zen model line.
Part of the canonical Zen5 ladder:
| SKU | Hardware fit | This repo |
|---|---|---|
zen5-flash |
anything (4 GB VRAM) | โ you are here |
zen5-mini |
hosted only | zen-5-mini-gguf |
zen5 (default) |
24 GB+ VRAM | zen-5-gguf |
zen5-pro |
Mac M4 Max / DGX Spark / H100 80GB | zen-5-pro-gguf |
zen5-max |
Mac Studio M3 Ultra 512GB / 8x H100 | zen-5-max-gguf |
Files
| File | Format |
|---|---|
model-00001-of-00002.safetensors + model-00002-of-00002.safetensors |
sharded safetensors |
tokenizer.json, tokenizer_config.json, special_tokens_map.json |
tokenizer |
config.json, generation_config.json |
model config |
chat_template.jinja |
chat template |
Run
Hosted via the Hanzo gateway (api.hanzo.ai) as zen5-flash โ see https://docs.hanzo.ai/zen.
Local with the zen5-engine or any transformers-compatible runtime:
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("zenlm/zen-5-flash-gguf")
model = AutoModelForCausalLM.from_pretrained("zenlm/zen-5-flash-gguf", device_map="auto")
License
apache-2.0. Upstream: Qwen/Qwen3-4B by Alibaba Qwen; abliterated variant by huihui-ai. This repository redistributes a derivative under the same license.
- Downloads last month
- 70