60 lines
2.3 KiB
Markdown
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.
|