GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
jtl11
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
jtl11
Model Tree
PrimeIntellect/INTELLECT-3
Input Modalities
Output Modalities
Supported Functionality
| Parameter | Value |
|---|---|
| direction_index | 26.50 |
| attn.o_proj.max_weight | 1.48 |
| attn.o_proj.max_weight_position | 27.79 |
| attn.o_proj.min_weight | 1.10 |
| attn.o_proj.min_weight_distance | 15.18 |
| mlp.down_proj.max_weight | 1.47 |
| mlp.down_proj.max_weight_position | 39.36 |
| mlp.down_proj.min_weight | 0.24 |
| mlp.down_proj.min_weight_distance | 17.75 |
| Metric | This model | Original model (0xSero/INTELLECT-3-REAP-50) |
|---|---|---|
| KL divergence | 0.0413 | 0 (by definition) |
| Refusals | 3/100 | 60/100 |
50% expert-pruned version of PrimeIntellect/INTELLECT-3 using Cerebras REAP (Router-weighted Expert Activation Pruning).
| Property | Value |
|---|---|
| Base Model | PrimeIntellect/INTELLECT-3 (248B MoE) |
| Architecture | GLM-4 MoE (glm4_moe) |
| Compression | 50% (64 experts pruned) |
| Remaining Experts | 64 per layer |
| Parameters | ~124B |
| Format | BF16 SafeTensors |
| Size | 107 GB |
yaml
dataset: 0xSero/glm47-reap-calibration-v2samples: 1360- evol-codealpaca-v1: 700 (code generation)- xlam-function-calling-60k: 330 (function calling)- SWE-smith-trajectories: 330 (agentic multi-turn)distance_measure: angularseed: 42model_max_length: 2048compression_ratio: 0.50prune_method: reap
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel = AutoModelForCausalLM.from_pretrained("0xSero/INTELLECT-3-REAP-50",torch_dtype="auto",device_map="auto",trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained("0xSero/INTELLECT-3-REAP-50", trust_remote_code=True)messages = [{"role": "user", "content": "Write a Python function to calculate fibonacci numbers"}]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)outputs = model.generate(inputs, max_new_tokens=512)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
| Model | Compression | Format | Size |
|---|---|---|---|
| INTELLECT-3-REAP-50 | 50% | BF16 | 107GB |
| INTELLECT-3-REAP-50-W4A16 | 50% | W4A16 GPTQ | ~30GB (coming soon) |
bibtex
@article{cerebras2025reap,title={REAP: Router-weighted Expert Activation Pruning for MoE Models},author={Cerebras Systems},year={2025}}
This model was created as part of efficiency research for large MoE models.