GLM 4.7 Flash NVFP4 by GadflyII — 18.44B open-weight local LLM. License: apache-2.0. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on slopsome.com.
Key specs
| Type | Local open-weight |
|---|
| Parameters | 18.44B total · MoE, — active |
|---|
| Architecture | glm4_moe_lite |
|---|
| Context window | 203K tokens |
|---|
| Knowledge cutoff | — |
|---|
| Modalities | text |
|---|
| Recommended backends | — |
|---|
| Minimum viable rig | — |
|---|
Benchmark scores
| GPQA Diamond | — |
|---|
| SWE-bench Verified | — |
|---|
| AIME | — |
|---|
| MMLU-Pro | — |
|---|
| BFCL v3 (tool use) | — |
|---|
| Composite score | — |
|---|
| Community rating | No reviews yet |
|---|
VRAM & disk per quantization
| Quant | VRAM | Disk | RAM | Context |
|---|
| Q4_K_M | 12.2 GB | 10.7 GB | — | 203K |