---
title: Qwen38-27B-Coder390-AIPod
canonical_url: "https://www.modelscope.cn/models/manateelazycat/Qwen38-27B-Coder390-AIPod"
md_url: "https://www.modelscope.cn/models/manateelazycat/Qwen38-27B-Coder390-AIPod.md"
repository: manateelazycat/Qwen38-27B-Coder390-AIPod
last_updated: 2026-10-13
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
parameters: 19.1B
tensor_type:
  - U8
  - BF16
  - F8_E4M3
  - F32
library_name:
  - safetensors
language:
  - zh
  - en
downloads: 208
stars: 0
tags:
  - qwen38-27b
  - coder390
  - nvfp4
  - aipod
  - jetson-thor
---

# Qwen38-27B-Coder390-AIPod

> Qwen38-27B-Coder390-AIPod - manateelazycat 在 ModelScope 开源的模型。Qwen 3.8 27B Coder390, Thor runtime and isolated LPK

manateelazycat/Qwen38-27B-Coder390-AIPod 是 ModelScope 魔搭社区上的 19.1B 参数text-generation模型，采用 apache-2.0 许可。

- **Repository**: manateelazycat/Qwen38-27B-Coder390-AIPod
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 19.1B
- **Tags**: qwen38-27b, coder390, nvfp4, aipod, jetson-thor
- **Downloads**: 208
- **Stars**: 0
- **Last updated**: 2026-10-13

Source: https://www.modelscope.cn/models/manateelazycat/Qwen38-27B-Coder390-AIPod

---

# Qwen 3.8 27B Coder390 for AI Pod

Independent LPK package: `cloud.lazycat.aipod.qwen38-27b-coder390`.

This repository contains the verified NVFP4 W4A4 target and FP8 DFlash2 snapshots, a separately published model-free Thor runtime, and the minimal LPK controller release. No files or release IDs of other Qwen 27B projects are updated.

Upstream model: [nerkyor Coder390](https://huggingface.co/nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2), fixed revision `bae2cbd736952a21006feca2630f5715016250c2`.

Target hardware: NVIDIA Thor SM110, 128 GB unified memory. Default context: 32768 tokens; scheduler limit: 8 requests. Performance reports identify their exact images and test conditions.

## Validated LPK release: 0.1.2

[huggingface](https://huggingface.co/manateelazycat/Qwen38-27B-Coder390-AIPod/resolve/eec39a8fa7dc8f8a4d40c8aaaea0a8c097cfc772/cloud.lazycat.aipod.qwen38-27b-coder390-v0.1.2.lpk) · [modelscope](https://modelscope.cn/models/manateelazycat/Qwen38-27B-Coder390-AIPod/resolve/bb9f8b2f5316772cfc2d688eba356bd4a5f16fdd/cloud.lazycat.aipod.qwen38-27b-coder390-v0.1.2.lpk)

LPK SHA256: `a732c042b3fd1cd549e539942c0f490332e2c04e10078791116ffd20012cb974`; size: 171008 bytes.

The 0.1.0 and 0.1.1 LPK files are incomplete release candidates. Use 0.1.2, which passed the installed source matrix on 192.168.1.160. The model snapshot and validated inference runtime retain their separate immutable identities.

The installation tests reused fully SHA256-verified model bytes in an independent device namespace; both public model snapshots were separately downloaded anonymously and fully verified. The final runtime was imported from an absent image state for both sources.

See `release-summary-0.1.2.html`, `release-summary-0.1.2.json`, and the profiling/validation evidence. Desktop/mobile entry and the real model-store card were tested; full LazyCat portal session login was not covered.