PAW-24B-X3.1 is an open-weight model from Irawan W, released under other. Its published files total 36.2 GB.
If this model is useful to you, support the work by following @nawariokra on X. LiquidAI/LFM2.5-24B-A2B (24B MoE, 2.3B active, 64 experts, top-4) at 6.9 - 11.2 GB, on one 24 GB RTX 3090 or smaller. Four GGUF files, one per expert bit rate.
Model Card
If this model is useful to you, support the work by following @nawariokra on X. LiquidAI/LFM2.5-24B-A2B (24B MoE, 2.3B active, 64 experts, top-4) at 6.9 - 11.2 GB, on one 24 GB RTX 3090 or smaller. Four GGUF files, one per expert bit rate. They run on our own engine TRUSS. Stock llama.cpp cannot read these files. How they are made: the routed experts (38 layers x 64 experts x gate/up/down) are encoded with the X3.1 trellis codec (exllamav3 encoder settings, activations from the BF16 model, calibration on 249 x 1,024 tokens of code), one uniform rate per file. Everything else (attention, short convolutions, dense FFN, shared parts, embeddings) is Q80, and the routers and their selection bias…
Excerpt from the card by Irawan W, licensed other.
Identity and Version
- Repository
- lackonendes/PAW-24B-X3.1
- Publisher
- Irawan W
- Task
- Not stated by the source
- Modality
- Other
- Library
- gguf
- Parameters
- Not stated by the source
- Languages
- moe, paw
- Revision
- d2eb5728f31fa6599d659008cf517408eae1a1f9
- First published
- 2026-10-14
- Last updated
- 2026-10-15
Files and Weights
6 files, 36.2 GB in total. The weights are 4 files totalling 36.2 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| PAW-24B-X3.1-K2.5.gguf | Weights | 8.3 GB | 10a8b5aae1be |
| PAW-24B-X3.1-K2.gguf | Weights | 6.9 GB | 3d6656437e51 |
| PAW-24B-X3.1-K3.5.gguf | Weights | 11.2 GB | 3066a56e351c |
| PAW-24B-X3.1-K3.gguf | Weights | 9.8 GB | b11db6451b35 |
| README.md | Documentation | 4.8 KB | — |
| .gitattributes | Repository | 1.8 KB | — |
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 36.2 GB
Released by Irawan W through its official repository on Hugging Face. Read the license.
Built From
- Derived from LiquidAI/LFM2.5-24B-A2B
- Quantized from LiquidAI/LFM2.5-24B-A2B
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 36.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About PAW-24B-X3.1
What license is PAW-24B-X3.1 released under?
other, as its publisher declares it. Read the license text before commercial use.