Apertus 70B Instruct 2509 Quantized.W4a16

RedHatAI · released 2025-09-21 · apache-2.0 license

Apertus 70B Instruct 2509 Quantized.W4a16 by RedHatAI — 11.31B open-weight local LLM. License: apache-2.0. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on slopsome.com.

Key specs

TypeLocal open-weight
Parameters11.31B total
Architectureapertus
Context window66K tokens
Knowledge cutoff
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond
SWE-bench Verified
AIME
MMLU-Pro
BFCL v3 (tool use)
Composite score
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M8.1 GB6.6 GB66K