OP

openPangu Embedded 1B

OpenpanguGGUF by mradermacherUpdated 2025-12-05
Download on Hugging Face
Parameters1.16B
Context32K
Layers26
Architecturepangu-embedded
Smallest quant0.0 GB
Quick answer

openPangu Embedded 1B needs about 1.9 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 1.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.6 GB.

openPangu Embedded 1B – 1.16B parameter language model for edge deployment

openPangu Embedded 1B is a 1.16B parameter language model with a 26‑layer Dense architecture. It was trained from scratch on Ascend NPU and is optimized for edge devices. The model supports a 32768 token context window.

Good at

  • Embedding generation
  • Edge‑side inference
  • Low‑memory deployment

Limits

  • No vision support
  • License is other
  • No mixture of experts

Best for

  • Embedding tasks in resource‑constrained environments
  • Fast inference on edge GPUs
  • Low‑latency text generation

Who it’s for. Developers building lightweight language applications on edge hardware. The model is suitable for projects that require a small footprint and fast inference without large GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.2 GB
Fits Get file →
IQ1_S0.4 GB 1.5 GB
Fits Get file →
IQ1_M0.4 GB 1.5 GB
Fits Get file →
IQ2_XXS0.4 GB 1.6 GB
Fits Get file →
IQ2_XS0.4 GB 1.6 GB
Fits Get file →
IQ2_S0.4 GB 1.6 GB
Fits Get file →
IQ2_M0.5 GB 1.6 GB
Fits Get file →
Q2_K_S0.5 GB 1.7 GB
Fits Get file →
IQ3_XXS0.5 GB 1.7 GB
Fits Get file →
Q2_K0.5 GB 1.7 GB
Fits Get file →
IQ3_XS0.6 GB 1.7 GB
Fits Get file →
IQ3_S0.6 GB 1.7 GB
Fits Get file →
Q3_K_S0.6 GB 1.7 GB
Fits Get file →
IQ3_M0.6 GB 1.8 GB
Fits Get file →
Q3_K_M0.6 GB 1.8 GB
Fits Get file →
Q3_K_L0.7 GB 1.8 GB
Fits Get file →
IQ4_XS0.7 GB 1.8 GB
Fits Get file →
IQ4_NL0.7 GB 1.9 GB
Fits Get file →
Q4_00.7 GB 1.9 GB
Fits Get file →
Q4_K_S0.7 GB 1.9 GB
Fits Get file →
Q4_K_M0.8 GB 1.9 GB
Fits Get file →
Q4_10.8 GB 1.9 GB
Fits Get file →
Q5_K_S0.8 GB 2.0 GB
Fits Get file →
Q5_K_M0.8 GB 2.0 GB
Fits Get file →
Q6_K1.0 GB 2.1 GB
Fits Get file →

For 8 GB VRAM, the Q4_K_M quant (~0.75 GB file, ~1.9 GB memory at 8 k context) is a good balance. If memory is tighter, IQ1_S (~0.36 GB file, ~1.5 GB memory) can be used. For the lowest memory usage, IQ2_XXS (~0.41 GB file, ~1.6 GB memory) is recommended.

What GPU do you need for openPangu Embedded 1B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q6_K (1.0 GB file, about 2.1 GB in use).

Which openPangu Embedded 1B quant should you choose?

Q4_K_M is the usual starting point for openPangu Embedded 1B: it balances file size and quality well. Here it is a 0.8 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturepangu-embedded
Parameters1.16B
Layers26
Trained context32,768 tokens
KV cache (fp16)78 KB per token

Source

Quantized bymradermacher
FamilyOpenpangu
Licenseother
Downloads (HF)563
Last updated2025-12-05

Frequently asked questions about openPangu Embedded 1B

How much VRAM does openPangu Embedded 1B need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 0.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run openPangu Embedded 1B on an 8 GB GPU?

Yes, with Q6_K: the 1.0 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of openPangu Embedded 1B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.4 GB, IQ1_M is 0.4 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB and 19 more.

What context length does openPangu Embedded 1B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.6 GB at 32K.

Where can I download openPangu Embedded 1B GGUF?

The files are on Hugging Face in the mradermacher/openPangu-Embedded-1B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does openPangu Embedded 1B use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run openPangu Embedded 1B on 8 GB VRAM?

Yes, the Q4_K_M quant requires approximately 1.9 GB of VRAM at 8 k context, which fits within an 8 GB budget.

Does the model support vision tasks?

No, the model only has language capabilities and does not include vision support.

What license applies to this model?

The model is licensed under an "other" license; refer to the LICENSE file in the repository for details.

Other GGUFs of openPangu-Embedded-1B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Openpangu models

All Openpangu →

Other tiny models

All tiny models →