HF Model & Benchmark Matrix
Overview
Benchmarks
Speech
Models
Orgs
24,078 variants · 14,984 scores · 120 benchmarks
Home
/
Orgs
/
ai-sage
/
ai-sage/GigaChat3-10B-A1.8B-bf16
ai-sage/GigaChat3-10B-A1.8B-bf16
family misc · 1 variants · unknown
provider
ai-sage
released
—
huggingface
https://huggingface.co/ai-sage/GigaChat3-10B-A1.8B-bf16
best scores
MMLU-Pro:
60.61
MATH-500:
70.0
LiveCodeBench:
20.31
Best scores per benchmark
benchmark
category
best score
MATH-500
math
70.0
MMLU-Pro
knowledge
60.61
LiveCodeBench
coding
20.31
Variants (1)
variant
kind
quant
bits
vRAM
dl
org
year
GigaChat3-10B-A1.8B-GGUF
gguf
gguf
16.0
206
Mungert
2025
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.