Aiqre

Model library / ai-sage

GigaChat3.5-432B-A28B-Reasoning

GigaChat 3.5 Reasoning is a 438 billion-parameter mixture-of-experts language model trained with online RL for improved reasoning tasks.

438.1B

8 of 256 experts active per token

262,144

Context length in tokens, as published

415 GiB

Weights at the released precision

mit

Licence declared on the repository

Overview

What this model is.

The model is a 432 billion-parameter GigaChat 3.5 variant that combines Multi-head Latent Attention with GatedDeltaNet linear-attention layers. It is presented by ai-sage as a reasoning-focused model, trained with online reinforcement learning and domain-specific reward signals to enhance mathematics, code, instruction following and structured output.

In practice the model contains 256 experts with eight active per token, yielding 28 billion active parameters. It supports a context window of 262 144 tokens, is released under an MIT licence and uses fp8 weight format. Deployment requires substantial GPU resources, for example eight H100 GPUs, and can be run via SGLang or vLLM with optional speculative decoding.

Specification

The published shape.

Repositoryai-sage/GigaChat3.5-432B-A28B-Reasoning
Publisherai-sage
Published3 September 2026
ArchitectureGigaChat35ForCausalLM
Model typegigachat3_5
Parameters438,085,063,424
Experts256 total, 8 active per token
Layers40
Hidden size7,168
Attention heads64, 64 key/value heads
Context length262,144 tokens
Vocabulary128,256 tokens
Quantisationfp8
Licencemit
Base modelai-sage/GigaChat3.5-432B-A28B-base

Memory

How much VRAM the weights need.

Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.

PrecisionWeightsNotes
bf16816.0 GiBFull precision as released
fp8408.0 GiB8-bit, near-lossless on most models
int4204.0 GiB4-bit, smallest footprint

The cache costs 1.1 MiB per token at 16-bit, so the full 262,144-token context of one request needs about 280.0 GiB. Concurrency multiplies that number, not the weights.

That figure is an upper bound: this model uses compressed key-value attention, so the real cache is a fraction of the figure above.

Hardware

Which card runs it.

At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.

GPUCards neededFree for cacheContext it holds
RTX 4090 24GB more than 8
RTX 5090 32GB more than 8
L40S 48GB more than 8
A100 80GB 8 140.7 GiB about 131,758 tokens
H100 80GB 8 140.7 GiB about 131,758 tokens
RTX PRO 6000 96GB 8 255.9 GiB about 239,611 tokens
H200 141GB 4 82.3 GiB about 77,082 tokens

Serving

Running it yourself.

A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.

vllm serve ai-sage/GigaChat3.5-432B-A28B-Reasoning \
  --tensor-parallel-size 8 \
  --max-model-len 131072 \
  --gpu-memory-utilization 0.90

Questions

The things people ask about this model.

How much GPU memory does GigaChat3.5-432B-A28B-Reasoning need?

The weights take about 415 GiB at the released precision. No single card in the table above holds that, so it needs several GPUs or a lower precision.

What licence does GigaChat3.5-432B-A28B-Reasoning use?

The repository declares mit. Read the licence text before commercial use: the name alone does not tell you what is allowed.

How long a context does it support?

The configuration allows 262,144 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.

Can I use it through an API instead of hosting it?

This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.

Also in the library

Related models.

nex-agi/Nex-N2.5-Pro

Nex-N2.5-Pro is a 396.8 billion-parameter MoE language model designed for long-horizon, agentic tasks with multimodal and compute…

IFM/K2-Horizon-375B-A23B

K2-Horizon-375B-A23B is an open-weight sparse MiE language model from IFM with 379 B parameters, 23 B active per token and a 512 …

tencent/Hy4-preview

Hy4 preview is a 780 billion-parameter mixture-of-experts language model released by Tencent for productivity-focused tasks.

zai-org/GLM-5.3

GLM-5.3 is a 753.3 billion-parameter open-weight mixture-of-experts language model for coding and security tasks.

Hosting

Want this model on a dedicated EU GPU?

Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.