OP

openPangu Embedded 1B V1.1

OpenpanguGGUF by noctrexUpdated 2025-11-05
Download on Hugging Face
Parameters1.16B
Context32K
Layers26
Architecturepangu-embedded
Smallest quant0.7 GB
Quick answer

openPangu Embedded 1B V1.1 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 11 quants, from 0.7 GB (IQ4_XS) to 4.6 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 2.6 GB.

1.16B parameter Openpangu embedded model for efficient local inference

openPangu-Embedded-1B-V1.1 is a 1.16B parameter language model designed for edge devices. It supports 32768 token context and is optimized for the Ascend Atlas 200I A2 platform. The model is available in multiple GGUF quantizations.

Good at

  • Embedding generation
  • Lightweight inference on edge
  • Fast token processing

Limits

  • No vision support
  • License not specified
  • Requires Ascend hardware for optimal performance

Best for

  • Local embedding tasks
  • Edge AI inference
  • Small‑scale language modeling

Who it’s for. Developers building lightweight language applications on edge hardware. Researchers needing a small, efficient model for on‑device inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS0.7 GB 1.8 GB
Fits Get file →
IQ4_NL0.7 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 →
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 →
Q8_01.2 GB 2.4 GB
Fits Get file →
BF162.3 GB 3.5 GB
Fits Get file →
F162.3 GB 3.5 GB
Fits Get file →
F324.6 GB 5.8 GB
Fits Get file →

For 8 GB VRAM, use IQ4_XS (0.69 GB, 1.8 GB memory) or Q4_K_S (0.72 GB, 1.9 GB memory). For 16 GB VRAM, Q5_K_M (0.85 GB, 2 GB memory) or Q6_K (0.95 GB, 2.1 GB memory) are suitable. Higher precision quantizations require more memory.

What GPU do you need for openPangu Embedded 1B V1.1?

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 BF16 (2.3 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is F32 (4.6 GB file, about 5.8 GB in use).

Which openPangu Embedded 1B V1.1 quant should you choose?

Q4_K_M is the usual starting point for openPangu Embedded 1B V1.1: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.2 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ4_XS at 0.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

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 bynoctrex
FamilyOpenpangu
Downloads (HF)702
Last updated2025-11-05

Frequently asked questions about openPangu Embedded 1B V1.1

How much VRAM does openPangu Embedded 1B V1.1 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 V1.1 on an 8 GB GPU?

Yes, with F32: the 4.6 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of openPangu Embedded 1B V1.1 GGUF?

It depends on the quant: IQ4_XS is 0.7 GB, IQ4_NL is 0.7 GB, Q4_K_S is 0.7 GB, Q4_K_M is 0.8 GB, Q5_K_S is 0.8 GB, Q5_K_M is 0.8 GB and 5 more.

What context length does openPangu Embedded 1B V1.1 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 V1.1 GGUF?

The files are on Hugging Face in the noctrex/openPangu-Embedded-1B-V1.1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run openPangu-Embedded-1B-V1.1 on 8 GB VRAM?

Yes, using IQ4_XS or Q4_K_S quantizations will fit within 8 GB VRAM with approximate memory usage of 1.8–1.9 GB at 8k context.

Does this model support vision tasks?

No, the model only provides language embedding capabilities.

What hardware is recommended for best performance?

The model is optimized for Ascend Atlas 200I A2 and similar edge devices; other hardware may run but with lower efficiency.

Other GGUFs of openPangu-Embedded-1B-V1.1

Similar models

Browse all →

More from noctrex

All by noctrex →

More Openpangu models

All Openpangu →

Other tiny models

All tiny models →