GLM 4.7 Flash REAP 23B A3B NVFP4

dmnsh · released 2026-07-27 · mit license

GLM 4.7 Flash REAP 23B A3B NVFP4 by dmnsh — 12.58B open-weight local LLM. License: mit. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on slopllm.com.

Key specs

TypeLocal open-weight
Parameters12.58B total · MoE, — active
Architectureglm4_moe_lite
Context window203K 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_M8.8 GB7.3 GB203K