Files
zen-5-flash-gguf/README.md
ModelHub XC 30197bd489 初始化项目,由ModelHub XC社区提供模型
Model: zenlm/zen-5-flash-gguf
Source: Original Platform
2026-08-21 19:53:12 +08:00

60 lines
2.3 KiB
Markdown

---
license: apache-2.0
base_model: Qwen/Qwen3-4B
library_name: transformers
pipeline_tag: text-generation
language:
- en
- zh
tags:
- zen5
- zen5-flash
- zenlm
- hanzo
- safetensors
- instruct
- agentic
- zen-5
---
# Zen5 Flash
Smallest and fastest tier in the [Zen5](https://zenlm.org) 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](https://huggingface.co/Qwen/Qwen3-4B) (apache-2.0, Alibaba Qwen) — redistributed as safetensors from the abliterated [huihui-ai/Qwen3-4B-abliterated](https://huggingface.co/huihui-ai/Qwen3-4B-abliterated) variant. **Not trained from scratch** — 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) | **← you are here** |
| `zen5-mini` | hosted only | [zen-5-mini-gguf](https://huggingface.co/zenlm/zen-5-mini-gguf) |
| `zen5` (default) | 24 GB+ VRAM | [zen-5-gguf](https://huggingface.co/zenlm/zen-5-gguf) |
| `zen5-pro` | Mac M4 Max / DGX Spark / H100 80GB | [zen-5-pro-gguf](https://huggingface.co/zenlm/zen-5-pro-gguf) |
| `zen5-max` | Mac Studio M3 Ultra 512GB / 8x H100 | [zen-5-max-gguf](https://huggingface.co/zenlm/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` — see https://docs.hanzo.ai/zen.
Local with the [zen5-engine](https://github.com/zenlm/zen5-engine) or any transformers-compatible runtime:
```python
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.