Instructions to use ai-sage/GigaChat3.5-432B-A28B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ai-sage/GigaChat3.5-432B-A28B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ai-sage/GigaChat3.5-432B-A28B-GGUF",
	filename="GigaChat3.5-432B-A28B-Q4_K_M/GigaChat3.5-432B-A28B-Q4_K_M-00001-of-00006.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ai-sage/GigaChat3.5-432B-A28B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ai-sage/GigaChat3.5-432B-A28B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ai-sage/GigaChat3.5-432B-A28B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai-sage/GigaChat3.5-432B-A28B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

Ollama
How to use ai-sage/GigaChat3.5-432B-A28B-GGUF with Ollama:
```
ollama run hf.co/ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M
```

Unsloth Studio

How to use ai-sage/GigaChat3.5-432B-A28B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ai-sage/GigaChat3.5-432B-A28B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ai-sage/GigaChat3.5-432B-A28B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ai-sage/GigaChat3.5-432B-A28B-GGUF to start chatting

How to use ai-sage/GigaChat3.5-432B-A28B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ai-sage/GigaChat3.5-432B-A28B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ai-sage/GigaChat3.5-432B-A28B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use ai-sage/GigaChat3.5-432B-A28B-GGUF with Docker Model Runner:
```
docker model run hf.co/ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M
```

Lemonade

How to use ai-sage/GigaChat3.5-432B-A28B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ai-sage/GigaChat3.5-432B-A28B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.GigaChat3.5-432B-A28B-GGUF-Q4_K_M

List all available models

lemonade list

How to use from the

Use from the

llama-cpp-python library

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ai-sage/GigaChat3.5-432B-A28B-GGUF",
	filename="",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

GigaChat 3.5 Ultra

GigaChat 3.5 Ultra is the flagship instant model of the GigaChat family. It is a large-scale Mixture-of-Experts (MoE) model with 432B total parameters, built on a custom hybrid attention architecture that combines Multi-head Latent Attention (MLA) with GatedDeltaNet linear-attention layers. The model targets multilingual assistant workloads, reasoning, code, agentic/tool-use scenarios, and large-cluster deployment.

Compared to the previous flagship GigaChat 3.1 Ultra (700B), version 3.5 is ~40% more compact yet stronger in code, mathematics, and agentic scenarios. It also uses roughly 4× less KV-cache per token, fits more than 2× more context into the same memory, and improves generation throughput by ~20%.

Version for high-performance inference in fp8 - GigaChat3.5-432B-A28B.

Model in bf16 is GigaChat3.5-432B-A28B-bf16.

Base version for training - GigaChat3.5-432B-A28B-base.

Training checkpoints - GigaChat3.5-432B-A28B-checkpoints.

More details can be found in the Habr article.

Model architecture

GigaChat 3.5 Ultra uses a custom MoE architecture. The core change relative to 3.1 is a self-designed hybrid architecture and a matching training recipe: every acceleration feature (linear attention, MTP) was paired with a stabilizing mechanism so the model could be trained to full scale without loss of stability.

Mixture-of-Experts (MoE)

The model has 432B total and 28B active parameters, keeping inference cost far below that of an equally large dense model. The MoE decoder layer is composed of attention, the MoE (expert) block, and a post-normalization applied before the residual add.

Hybrid attention: MLA + GatedDeltaNet

Standard attention grows more expensive with context length: the longer the request, the larger the KV-cache, and the more generation is bottlenecked on memory. GigaChat 3.5 introduces a hybrid design in which some layers remain regular MLA and the rest are linear-attention layers based on GatedDeltaNet. This preserves the strengths of full attention while lowering the cost of long context.

Gated Normalization (GatedNorm)

Large models tend to develop implicit self-stabilization (attention/residual sinks), routing most of the signal through a single token or feature to hold the activation scale — which is poorly controlled and can itself become a source of noise at scale. GatedNorm replaces these implicit anchors with an explicit multiplicative gate after RMSNorm, letting the network rescale the signal across features directly. It is made scale-neutral at init via the 2 · sigmoid reparametrization (a plain sigmoid starts near 0.5 and would halve the scale; the factor 2 keeps the gate near 1.0), so it barely perturbs the data flow at start and learns where to attenuate.

Multi-Token Prediction (MTP)

GigaChat Ultra 3.0 had a single MTP head; in GigaChat Ultra 3.5 we added two MTP heads. Greedy decoding accelerates the generation speed ~1.5× with one head and up to 2.2× with two.

Precision and optimizer

The model was trained in native FP8 across all training stages. We also release dequantized bf16 checkpoint.

Alignment

The post-training pipeline runs Stage 1.5 → SFT → DPO → Online RL. Online RL is the headline addition of this release and drove the gains in Instruction Following and on arenas.

Benchmark scores

Base-model

GENERAL

Task	GigaChat 3.1 Base (700B)	GigaChat-3.5-Ultra-Base (430B)	DeepSeek V4 Flash Base (284B)	DeepSeek V3.2 Exp Base (685B)
MMLU (5-shot)	79.89	85.28	88.68	87.47
MMLU-Pro (5-shot)	68.01	74.54	65.86	62.43
GPQA Diamond (official, CoT)	30.3	30.81	22.73	22.22
BBH (3-shot)	83.78	87.5	88.24	89.16
ARC-C (25-shot, acc_norm)	68.34	70.39	72.35	70.31
ARC-E (25-shot, acc_norm)	88.38	88.59	90.82	89.27
HellaSwag (10-shot, acc_norm)	89.43	89.47	88.9	89.28
Winogrande (5-shot)	82.72	85	84.61	84.93
DROP (5-shot, EM)	56.29	59.55	63.88	65.14
TriviaQA (5-shot, EM)	81.4	82.23	83.96	83.88
NQ-Open (5-shot, EM)	37.34	41.66	40.83	42.27
Avg	69.6	72.3	71.9	71.5

MATH

Task	GigaChat 3.1 Base (700B)	GigaChat-3.5-Ultra-Base (430B)	DeepSeek V4 Flash Base (284B)	DeepSeek V3.2 Exp Base (685B)
MATH Minerva (math-verify)	55.78	61.7	54.74	58.2
GSM8K (CoT, math_verify)	86.73	86.58	86.43	84.99
MGSM ru (CoT)	87.6	86	84.4	82
Avg	76.7	78.1	75.2	75.1

CODE

Task	GigaChat 3.1 Base (700B)	GigaChat-3.5-Ultra-Base (430B)	DeepSeek V4 Flash Base (284B)	DeepSeek V3.2 Exp Base (685B)
HumanEval (pass@1)	70.12	80.49	66.46	64.02
HumanEval+ (pass@1)	62.8	75.61	61.59	56.71
MBPP (pass@1)	70.2	70.4	70.2	70.4
MBPP+ (pass@1)	83.33	83.33	77.25	82.28
CRUXEval (pass@1)	64.56	67.5	69.75	69.94
LCB CodeGen Lite	49.29	54.31	57.25	50.24
Avg	66.7	71.9	67.1	65.6

Instruct-model

Task	GigaChat-3.1-Ultra (700B)	GigaChat-3.5-Ultra (430B)	DeepSeek V3.2* (685B)
TAU2-bench	41.87	68.71	66
SWE bench verified **	8.6	42.6	44.8
Terminal bench 2 ***	9	13.48	29.21
Live Code Bench v6	49.29	56.2	59.3
Natural Plan	31.6	27.14	20.44
IFBench	31	43.66	45
MERA Text	71.2	67.3	61.7
Pollux	37.75	65.21	65.6
MMLU-Pro	73.61	75.68	81.1
RubQ_Ru	76.11	81.01	78.33
MATH 500	83	86	91.4
Arena Hard Logs vs GPT-5	55.5	71.4	71.3
Arena Hard Ru vs GPT-5	38.3	69.5	69.3
Ru LLM Arena vs GPT-5	38.2	62.9	63.6
Validator-SBS-Pollux	47.6	70.9	68
Avg	46.2	60.1	61.0

Notes:

* DeepSeek V3.2 is the instruct version
** SWE-bench Verified uses mini-swe-agent, 250 steps
*** Terminal-Bench 2 uses the terminus-2 agent

Speed

GPU (8 × H100, single stream, 192 tok/prompt)

quant	config	accept rate	decode tok/s	speedup
Q6_K	no MTP	—	47.2	1.00×
Q6_K	MTP-1	0.880	65.4	1.39×
Q6_K	MTP-2	0.775	69.2	1.47×
Q4_K_M	no MTP	—	58.4	1.00×
Q4_K_M	MTP-1	0.858	78.4	1.34×
Q4_K_M	MTP-2	0.759	84.0	1.44×

CPU (Intel Xeon 8462Y+, `-t 64`, 128 tok/prompt)

quant	config	accept rate	decode tok/s	speedup
Q4_K_M	no MTP	—	7.7	1.00×
Q4_K_M	MTP-1	0.880	8.6	1.12×
Q4_K_M	MTP-2	0.788	9.6	1.25×
Q6_K	no MTP	—	5.7	1.00×
Q6_K	MTP-1	0.876	7.0	1.23×
Q6_K	MTP-2	0.797	7.5	1.32×
Q8_0	no MTP	—	4.8	1.00×
Q8_0	MTP-1	0.886	5.7	1.19×
Q8_0	MTP-2	0.770	6.2	1.29×

Usage Example

Prepare the model

# 1. get the PR
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
git fetch origin pull/25342/head:pr-25342
git checkout pr-25342

# 2. download the GGUF (Q8_0 shown; Q4_K_M / Q6_K / bf16 also available)
pip install -U "huggingface_hub[cli]"
hf download ai-sage/GigaChat-3.5-432B-A28B-GGUF \
  --include "GigaChat3.5-432B-A28B-Q8_0/*" \
  --local-dir ./gguf

GPU

Build server

cd llama.cpp
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release -j --target llama-server

Start the server

./build/bin/llama-server \
  -m ./gguf/GigaChat3.5-432B-A28B-Q8_0/GigaChat3.5-432B-A28B-Q8_0-00001-of-00010.gguf \
  -ngl 99 \
  -fa on \
  -c 32768 \
  -np 4 \
  -ctk q8_0 -ctv q8_0 \
  --jinja \
  --spec-type draft-mtp \
  --spec-draft-n-max 2 \
  --host 0.0.0.0 --port 8080

CPU

Build server

cd llama.cpp
cmake -B build-cpu -DGGML_CUDA=OFF
cmake --build build-cpu --config Release -j --target llama-server

Start the server

./build-cpu/bin/llama-server \
  -m ./gguf/GigaChat3.5-432B-A28B-Q8_0/GigaChat3.5-432B-A28B-Q8_0-00001-of-00010.gguf \
  -ngl 0 \
  -t $(nproc) \
  -fa on \
  -c 32768 \
  -np 4 \
  -ctk q8_0 -ctv q8_0 \
  --jinja \
  --spec-type draft-mtp --spec-draft-n-max 2 \
  --host 0.0.0.0 --port 8080

Request example

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ai-sage/GigaChat3.5-432B-A28B-Q8_0",
  "chat_template_kwargs": {
      "enable_thinking": false
    },
  "temperature": 0,
  "messages": [
    {
      "role": "user",
      "content": "Какая сейчас погода в Москве?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Получить информацию о текущей погоде в указанном городе.",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string",
              "description": "Название города (например, Москва, Казань)."
            }
          },
          "required": ["city"]
        }
      }
    }
  ]
}'

Downloads last month: -

GGUF

Model size

434B params

Architecture

gigachat35

Hardware compatibility

4-bit

6-bit

8-bit

16-bit

Collection including ai-sage/GigaChat3.5-432B-A28B-GGUF

GigaChat 3.5

Collection

GigaChat 3.5 is a large-scale Mixture-of-Experts (MoE) Hybrid model with 432B total parameters • 5 items • Updated about 18 hours ago • 4

GigaChat 3.5 Ultra

Model architecture

Mixture-of-Experts (MoE)

Hybrid attention: MLA + GatedDeltaNet

Gated Normalization (GatedNorm)

Multi-Token Prediction (MTP)

Precision and optimizer

Alignment

Benchmark scores

Base-model

GENERAL

MATH

CODE

Instruct-model

Speed

GPU (8 × H100, single stream, 192 tok/prompt)

CPU (Intel Xeon 8462Y+, -t 64, 128 tok/prompt)

Usage Example

GPU

CPU

Request example

Collection including ai-sage/GigaChat3.5-432B-A28B-GGUF

CPU (Intel Xeon 8462Y+, `-t 64`, 128 tok/prompt)