GLM — REAP Collection REAP-pruned & quantized GLM-4.x / 5 / 5.1 (+ Flash fine-tunes). • 34 items • Updated 18 days ago • 2
GLM-5.3 REAP EXL3 Quantization Suite Collection Expert-pruned GLM-5.3 (753B) in EXL3. Massmax criterion, routed experts quantized, sensitive layers BF16. Ladder 500B-661B. • 7 items • Updated 18 days ago
GLM-5.3 REAP W4A16 (Hopper) Collection Expert-pruned GLM-5.3 in INT4 W4A16 (compressed-tensors) for 4x H200 serving. Built on cyankiwi/GLM-5.3-AWQ-INT4. Massmax criterion. • 2 items • Updated 18 days ago
GLM-5.3 REAP EXL3 Quantization Suite Collection Expert-pruned GLM-5.3 (753B) in EXL3. Massmax criterion, routed experts quantized, sensitive layers BF16. Ladder 500B-661B. • 7 items • Updated 18 days ago