ai-sage / deepseek_v3

GigaChat3.1-Audio-10B-A1.8B

Name: GigaChat3.1-Audio-10B-A1.8B architecture and memory requirements
Creator: LLM Bottleneck
License: https://creativecommons.org/licenses/by/4.0/

Parameter count not published, routing 4 of 64 experts per token.

Architecturepublished data

Architecture available · weight sizes unavailable

Weight sizeno data

This snapshot holds GigaChat3.1-Audio-10B-A1.8B’s architecture but no weight size for any format, so the calculator cannot answer for it and it has no hardware table.

Why: Neither a published artifact nor a published parameter count exists for this model at its pinned revision. A size is never inferred from the model’s name.

The coverage page explains what the catalogue does not size, and why.

Under the hood

Architecture, read from the publisher’s file

The numbers every figure above is computed from, with the file they came from.

Architecture

architecture.json · pinned bf73d03a43bd

✓ Architecture read from the published config.json

Retrieved 2026-09-01 at pinned commit bf73d03a43bd.

Architecture: deepseek_v3
Layers: 26
Hidden size: 1,536
Attention heads: 32
KV heads: 32
Head dimension: 64
Feed-forward width: 8,960
Vocabulary: 128,256
Context ceiling: 262,144
RoPE theta: 100,000
Experts: 64
Experts / token: 4
Expert width: 1,280
Shared experts: 1
Latent KV rank: 512

Where the memory goes

Latent attention projects keys and values into a compressed rank before caching them, which is why its KV cache is a fraction of a comparable dense model.

Open the exact official config.json ↗

More from ai-sage

GigaChat3.5-432B-A28B-Reasoning

Citing this page

LLM Bottleneck. “GigaChat3.1-Audio-10B-A1.8B VRAM and hardware requirements.” Architecture from ai-sage/GigaChat3.1-Audio-10B-A1.8B at revision bf73d03a43bd, retrieved 2026-09-01. https://llmbottleneck.com/models/ai-sage-gigachat3-1-audio-10b-a1-8b

Every figure above is either the published value or a reconstruction whose measured error is on the accuracy page.