Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/angelslim
Tencent AngelSlim — accessible, comprehensive, and efficient toolkit for large model compression. Quantization (FP8/INT4/NVFP4/1.25-bit), pruning, speculative decoding (Eagle3), and diffusion model compression.
Passed 21 of 22 test cases with the skill, and 9 of 22 without it.
and 13 more in the full report
12 fixed9 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
What exact weight precision (in bits) does the Sherry compression method achieve?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies 1.25-bit precision for Sherry | Missed | Passed |
The instructions your model reads when the skill loads.
AngelSlim integrates mainstream compression algorithms into a unified framework with one-click access. Supports FP8/INT8/INT4/NVFP4/1.25-bit quantization, pruning, Eagle3 speculative decoding, and diffusion model compression for LLMs, VLMs, and audio models.
uv pip install angelslim
import angelslim as slim
# FP8 static quantization
model = slim.quantize(model, dtype="fp8_static", qconfig="default")
# INT4 GPTQ
model = slim.quantize(model, dtype="int4_gptq", dataset="wikitext2")
| Method | Precision | Best For |
|---|---|---|
| FP8-Static/Dynamic | 8-bit | General LLM deployment |
| INT4 GPTQ/AWQ/GPTAQ | 4-bit | Memory-constrained serving |
| NVFP4 | 4-bit (NVIDIA) | Blackwell GPUs |
| Sherry | 1.25-bit | Extreme compression |
| STQ1_0 | 1.25-bit | On-device deployment |
# Train Eagle3 draft model
slim.eagle3.train(model, draft_model_config)
# Inference with Eagle3
output = model.generate_with_eagle3(input_ids, max_new_tokens=256)
test cases passed, vs 9 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.