openpangu · text · mixture of experts
openPangu-2.0-Flash
openpangu/openPangu-2.0-FlashopenPangu-2.0-Flash at Q4_K_M is exactly 55,275,517,568 bytes (51.48 GiB / 55.28 GB) — an effective 4.416 bits per weight, not the nominal 4.
From the file· summed from 1 file(s)From the file· KV per layer
Parameters
100B
total, not active
Architecture
openpangu-v2
46 layers
Context
524,288
native (config.json)
License
other
Shipped quantizations
● exact bytes, summed from published files
KV cache by context
unresolved
This model declares a 512-token sliding window, but we could not establish which layers use it. Its architecture publishes the layout as a per-layer array inside the model file rather than as a period in config.json, and we have not yet ingested that array.
A flat context × layers × heads figure would be substantially too high, so we are not showing one. This is tracked as a known gap rather than filled with a guess.
Compare with
same modality, comparable size
Will it run on your card?
full quant x context sweep
Radeon RX 6500 XT 4GBGeForce RTX 3050 6GBGeForce RTX 5050 8GBGeForce RTX 3080 10GBGeForce RTX 2080 Ti 11GBGeForce RTX 5070 12GBGeForce RTX 5060 Ti 16GBApple M3 Pro 18GBGeForce RTX 3080 Ti 20GBGeForce RTX 5090 D V2 24GBGeForce RTX 5090 D 32GBApple M5 Max 36GBApple M5 Pro 48GBApple M5 Max 64GBApple M3 Ultra 96GBApple M5 Max 128GBApple M2 Ultra 192GBApple M3 Ultra 256GBApple M3 Ultra 512GB
Why other calculators give a different number
A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 52.46 GiB. The real file is 51.48 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.
Architecture
from config.json
Layers
46
Attention heads
48
KV heads
48
Head dim
192
Hidden size
2560
Vocab
151,552
Sliding window
512
SWA period
—
MLA
yes
Experts
256
Experts per token
8
use_sliding_window
—
Questions people ask
- How much VRAM does openPangu-2.0-Flash need?
- Q4_K_M is exactly 55,275,517,568 bytes (51.48 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
- Is openPangu-2.0-Flash a mixture-of-experts model?
- Yes — 256 experts, 8 routed per token. Every expert must be resident, but only the routed ones are read per token, which is why its memory requirement and its speed behave very differently.
- Which quantization of openPangu-2.0-Flash should I use?
- Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.