At a glance
Table | |
|---|
| Base model | cerebras/GLM-4.6-REAP-218B-A32B |
| Format | W4A16 |
| Total params | 218B |
| Active / token | 32B |
| Experts / layer | 96 |
| Layers | 92 |
| Hidden size | 5120 |
| Context | 202,752 |
| On-disk size | 119 GB |
GLM-4.6-REAP-218B-A32B-W4A16-AutoRound
W4A16 quantized version of Cerebras' official GLM-4.6-REAP-218B-A32B.
- ~4x Size Reduction: ~436GB → ~116GB
- Runs on Consumer Hardware: 8x RTX 3090 or 4x RTX 4090
- vLLM/SGLang Compatible: Drop-in deployment
📋 Model Specifications
Table with columns: Property, Value| Property | Value |
|---|
| Base Model | cerebras/GLM-4.6-REAP-218B-A32B |
| Parameters | 218B total, 32B activated |
| Quantization | W4A16 (4-bit weights, 16-bit activations) |
| Original Size | ~436GB |
| Quantized Size | ~116GB |
🔬 Calibration Dataset: Deep Dive
REAP's effectiveness depends critically on calibration data that represents the target use case. We specifically optimized for code generation, function/tool calling, and agentic workflows.
Why These 3 Datasets?
Table with columns: Dataset, Samples, Purpose, Why It Matters| Dataset | Samples | Purpose | Why It Matters |
|---|
| evol-codealpaca-v1 | 700 | Code generation | 51% of mix — Code tasks activate specific expert pathways; pruning without code calibration destroys coding ability |
| xlam-function-calling-60k | 330 | Function/tool calling | 24% of mix — Tool use requires structured JSON output; experts handling schema generation must be preserved |
| SWE-smith-trajectories |
The Science Behind Dataset Selection
REAP Algorithm:
1. Forward pass calibration samples through model
2. Record which experts activate and their magnitudes
3. Compute saliency = router_weight × activation_norm
4. Prune lowest-saliency experts
Key Insight: Experts are TASK-SPECIFIC
├── Some experts specialize in natural language
├── Some experts specialize in code syntax
├── Some experts specialize in JSON/structured output
└── Some experts specialize in multi-turn context
If calibration lacks code → code-specialized experts appear "unused" → get pruned → model loses coding ability
Cerebras' Original Mix (from paper)
Cerebras used the same 3 datasets in their GLM-4.6 REAP experiments:
- evol-codealpaca-v1 for code generation
- xlam-function-calling-60k for tool calling
- SWE-smith-trajectories for agentic tasks
We followed this exact recipe for reproducibility.
Combined Dataset
Our calibration mix: 0xSero/glm47-reap-calibration-v2
License & citation
License inherited from the base model.
@misc{lasby2025reap,
title = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
year = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
}
Made possible by NVIDIA · TNG Technology · Lambda · Prime Intellect · Hot Aisle.