SAVRN
Search Contact SAVRN

Open-weight model · Text generation

RK182X-LLM-Qwen3-4B-Instruct-2507

by RKNNAI RKNNAI/RK182X-LLM-Qwen3-4B-Instruct-2507

RK182X-LLM-Qwen3-4B-Instruct-2507 is an open-weight model for text generation from RKNNAI, released under Apache License 2.0. Its published files total 6.5 GB. It draws 1 downloads a month.

本仓库提供由 Qwen/Qwen3-4B-Instruct-2507 转换得到的 RKNN LLM 模型。 - Model ID:RKNNAI/RK182X-LLM-Qwen3-4B-Instruct-2507 - 模型显示名称:RK182X-LLM-Qwen3-4B-Instruct-2507 - 源模型:Qwen/Qwen3-4B-Instruct-2507 - 模型类型:LLM ModelScope 完整下载: Hugging Face 完整下载: ModelScope 指定配置下载: Hugging…

Parameters—
Context—
Weights1.6 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1

Model Card

By RKNNAI, published under apache-2.0, revision 0e647c2ba12b.

本仓库提供由 Qwen/Qwen3-4B-Instruct-2507 转换得到的 RKNN LLM 模型。 - Model ID:RKNNAI/RK182X-LLM-Qwen3-4B-Instruct-2507 - 模型显示名称:RK182X-LLM-Qwen3-4B-Instruct-2507 - 源模型:Qwen/Qwen3-4B-Instruct-2507 - 模型类型:LLM ModelScope 完整下载: Hugging Face 完整下载: ModelScope 指定配置下载: Hugging Face 指定配置下载: - 使用配套 RKNN Runtime 和驱动;运行前用 rknn-smi -v 检查设备端版本。 源模型许可证见根目录 LICENSE;同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

Read RKNNAI's full model card

1. 模型介绍

本仓库提供由 Qwen/Qwen3-4B-Instruct-2507 转换得到的 RKNN LLM 模型。

  • Model ID:RKNNAI/RK182X-LLM-Qwen3-4B-Instruct-2507
  • 模型显示名称:RK182X-LLM-Qwen3-4B-Instruct-2507
  • 发布版本:v1.1.0
  • 源模型:Qwen/Qwen3-4B-Instruct-2507
  • 模型类型:LLM
  • 芯片字段:RK182X
  • 具体支持芯片:RK1828

可用模型

发布版本 配置目录 支持芯片 量化方式 NPU 核数 上下文长度(tokens) KVCache
v1.1.0 Qwen3-4B-Instruct-2507-w4a16-8-16896 RK1828 w4a16 8 16896(16.5k) fp16
v1.1.0 Qwen3-4B-Instruct-2507-w4a16-8-39424-kv-int4 RK1828 w4a16 8 39424(38.5k) int4

2. 文件说明

文件或目录 说明
LICENSE 源模型许可证
<配置目录>/ 配套模型文件
子目录 README.md 当前配置说明
子目录 config.json 模型配置与文件清单
子目录 SHA256SUMS 当前目录交付文件的 SHA-256 校验值(不包含自身)

3. 模型下载

ModelScope 完整下载:

modelscope download --model RKNNAI/RK182X-LLM-Qwen3-4B-Instruct-2507 --revision v1.1.0 --local_dir ./RK182X-LLM-Qwen3-4B-Instruct-2507

Hugging Face 完整下载:

hf download RKNNAI/RK182X-LLM-Qwen3-4B-Instruct-2507 --revision v1.1.0 --local-dir ./RK182X-LLM-Qwen3-4B-Instruct-2507

ModelScope 指定配置下载:

from modelscope import snapshot_download

snapshot_download(
    "RKNNAI/RK182X-LLM-Qwen3-4B-Instruct-2507",
    revision="v1.1.0",
    allow_patterns=["README.md", "LICENSE", "Qwen3-4B-Instruct-2507-w4a16-8-16896/**"],
    local_dir="./RK182X-LLM-Qwen3-4B-Instruct-2507",
)

Hugging Face 指定配置下载:

hf download RKNNAI/RK182X-LLM-Qwen3-4B-Instruct-2507 --revision v1.1.0 --include "README.md" "LICENSE" "Qwen3-4B-Instruct-2507-w4a16-8-16896/**" --local-dir ./RK182X-LLM-Qwen3-4B-Instruct-2507

4. SHA-256 校验

在配置目录执行:

cd ./RK182X-LLM-Qwen3-4B-Instruct-2507/Qwen3-4B-Instruct-2507-w4a16-8-16896
sha256sum -c SHA256SUMS

所有条目显示 OK 后再部署。

5. 兼容性与限制

  • 支持芯片:RK1828。
  • 使用配套 RKNN Runtime 和驱动;运行前用 rknn-smi -v 检查设备端版本。
  • 所选配置目录内的文件须配套使用。

6. 版权与许可证

源模型许可证见根目录 LICENSE;同时遵守 RKNN Toolkit 和 RKNN Runtime 许可条款。

Identity and Version

Repository
RKNNAI/RK182X-LLM-Qwen3-4B-Instruct-2507
Publisher
RKNNAI
Task
Text generation
Modality
Text
Library
Not stated by the source
Parameters
Not stated by the source
Languages
llm
Revision
0e647c2ba12b7034c724e4638542093a764ec5a3
First published
2026-09-24
Last updated
2026-09-28

Files and Weights

19 files, 6.5 GB in total. The weights are 4 files totalling 1.6 GB in bin, gguf.

Weights4 files · 1.6 GB
Configuration2 files · 2.2 KB
Documentation4 files · 18.6 KB
Other8 files · 5.0 GB
Repository1 file · 2.2 KB
Every file
FileTypeSizeSHA-256
Qwen3-4B-Instruct-2507-w4a16-8-16896/Qwen3-4B-Instruct-2507.embed.binWeights777.9 MB 4a97ee150176
Qwen3-4B-Instruct-2507-w4a16-8-16896/Qwen3-4B-Instruct-2507.tokenizer.ggufWeights5.9 MB 4a5a7b22a1e5
Qwen3-4B-Instruct-2507-w4a16-8-39424-kv-int4/Qwen3-4B-Instruct-2507.embed.binWeights777.9 MB 4a97ee150176
Qwen3-4B-Instruct-2507-w4a16-8-39424-kv-int4/Qwen3-4B-Instruct-2507.tokenizer.ggufWeights5.9 MB 4a5a7b22a1e5
Qwen3-4B-Instruct-2507-w4a16-8-16896/config.jsonConfiguration1.1 KB —
Qwen3-4B-Instruct-2507-w4a16-8-39424-kv-int4/config.jsonConfiguration1.1 KB —
LICENSEDocumentation11.3 KB —
Qwen3-4B-Instruct-2507-w4a16-8-16896/README.mdDocumentation2.2 KB —
Qwen3-4B-Instruct-2507-w4a16-8-39424-kv-int4/README.mdDocumentation2.2 KB —
README.mdDocumentation2.9 KB —
Qwen3-4B-Instruct-2507-w4a16-8-16896/Qwen3-4B-Instruct-2507.rknnOther37.6 MB 1ab75997a1fe
Qwen3-4B-Instruct-2507-w4a16-8-16896/Qwen3-4B-Instruct-2507.weightOther2.4 GB 50164a92d540
Qwen3-4B-Instruct-2507-w4a16-8-16896/SHA256SUMSOther631 B —
Qwen3-4B-Instruct-2507-w4a16-8-16896/model_report.htmlOther1.0 MB —
Qwen3-4B-Instruct-2507-w4a16-8-39424-kv-int4/Qwen3-4B-Instruct-2507.rknnOther65.3 MB 8f51c0f9a004
Qwen3-4B-Instruct-2507-w4a16-8-39424-kv-int4/Qwen3-4B-Instruct-2507.weightOther2.4 GB 50164a92d540
Qwen3-4B-Instruct-2507-w4a16-8-39424-kv-int4/SHA256SUMSOther631 B —
Qwen3-4B-Instruct-2507-w4a16-8-39424-kv-int4/model_report.htmlOther1.3 MB —
.gitattributesRepository2.2 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
1.6 GB
Download from RKNNAI

Released by RKNNAI through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published1.6 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About RK182X-LLM-Qwen3-4B-Instruct-2507

Can I use RK182X-LLM-Qwen3-4B-Instruct-2507 commercially?

Yes. RK182X-LLM-Qwen3-4B-Instruct-2507 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Fine-tune Qwen3 (14B) for free using our Google Colab notebook! - Read our Blog about Qwen3 support: unsloth.ai/blog/qwen3 - View the rest of our notebooks in our docs here. Qwen3-Coder is available in multiple sizes. Today, we're excited to introduce Qwen3-Coder-30B-A3B-Instruct. This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements: - Significant Performance among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks. - Long-context Capabilities with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale understanding. - Agentic Coding supporting for…

Open weights apache-2.0 transformers

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

Model · Text generation

Ternary-Bonsai-2-27B-gguf

Prism ML

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at about 82% of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at 74.92…

Open weights apache-2.0 llama.cpp

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers