Theprint Moe 8x3 0126 needs about 12.5 GB of memory at Q4_K_M (a 11.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 0.0 GB to 14.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
18B Mixture of Experts Llama model with 8×3B experts
Theprint Moe 8x3 0126 is an 18B parameter Mixture of Experts model built on Llama architecture. It contains 8 specialized 3B experts, with 2 experts activated per token by default. The model supports a context length of 131072 tokens and is licensed under Apache‑2.0.
Good at
- Tool‑using tasks
- Large‑context conversations
- Expert‑specific inference
Limits
- No vision support
- Requires at least 8k context for estimates
- License restricts commercial redistribution
Best for
- Chatbots needing domain expertise
- Long‑form content generation
- Research prototyping
Who it’s for. Developers and researchers who need a large‑parameter LLM with expert specialization and a flexible router. The model is suitable for inference setups that can handle the memory demands of Mixture of Experts architectures.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.5 GB | Fits | Get file → | |
| IQ1_S | 4.0 GB | 5.4 GB | Fits | Get file → | |
| IQ1_M | 4.4 GB | 5.8 GB | Fits | Get file → | |
| IQ2_XXS | 5.0 GB | 6.5 GB | Fits | Get file → | |
| IQ2_XS | 5.6 GB | 7.0 GB | Fits | Get file → | |
| IQ2_S | 5.6 GB | 7.1 GB | Fits | Get file → | |
| IQ2_M | 6.1 GB | 7.6 GB | Tight | Get file → | |
| Q2_K_S | 6.4 GB | 7.8 GB | Tight | Get file → | |
| Q2_K | 6.9 GB | 8.4 GB | Too big | Get file → | |
| IQ3_XXS | 7.2 GB | 8.6 GB | Too big | Get file → | |
| IQ3_XS | 7.7 GB | 9.1 GB | Too big | Get file → | |
| IQ3_S | 8.1 GB | 9.5 GB | Too big | Get file → | |
| Q3_K_S | 8.1 GB | 9.5 GB | Too big | Get file → | |
| IQ3_M | 8.5 GB | 9.9 GB | Too big | Get file → | |
| Q3_K_M | 8.9 GB | 10.3 GB | Too big | Get file → | |
| Q3_K_L | 9.5 GB | 10.9 GB | Too big | Get file → | |
| IQ4_XS | 9.8 GB | 11.3 GB | Too big | Get file → | |
| IQ4_NL | 10.4 GB | 11.8 GB | Too big | Get file → | |
| Q4_0 | 10.4 GB | 11.8 GB | Too big | Get file → | |
| Q4_K_S | 10.4 GB | 11.9 GB | Too big | Get file → | |
| Q4_K_M | 11.1 GB | 12.5 GB | Too big | Get file → | |
| Q4_1 | 11.4 GB | 12.9 GB | Too big | Get file → | |
| Q5_K_S | 12.5 GB | 14.0 GB | Too big | Get file → | |
| Q5_K_M | 12.9 GB | 14.3 GB | Too big | Get file → | |
| Q6_K | 14.8 GB | 16.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 11.09 GB, memory 12.5 GB at 8k context). For 12 GB VRAM, Q5_K_M (12.89 GB, 14.3 GB). For 16 GB VRAM, Q6_K (14.83 GB, 16.3 GB). Estimates are approximate.
What GPU do you need for Theprint Moe 8x3 0126?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.5 GB in use).
- 6 GB VRAM: the best quant that fits is IQ1_M (4.4 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K_S (6.4 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_S (10.4 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (12.9 GB file, about 14.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (14.8 GB file, about 16.3 GB in use).
Which Theprint Moe 8x3 0126 quant should you choose?
Q4_K_M is the usual starting point for Theprint Moe 8x3 0126: it balances file size and quality well. Here it is a 11.1 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Theprint Moe 8x3 0126
How much VRAM does Theprint Moe 8x3 0126 need?
About 12.5 GB at Q4_K_M with an 8K context window. That is the 11.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Theprint Moe 8x3 0126 on an 8 GB GPU?
Yes, with Q2_K_S: the 6.4 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Theprint Moe 8x3 0126 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 4.0 GB, IQ1_M is 4.4 GB, IQ2_XXS is 5.0 GB, IQ2_XS is 5.6 GB, IQ2_S is 5.6 GB and 19 more.
What context length does Theprint Moe 8x3 0126 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Theprint Moe 8x3 0126 GGUF?
The files are on Hugging Face in the mradermacher/theprint-moe-8x3-0126-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Theprint Moe 8x3 0126 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Use the Q4_K_M quant; it requires about 12.5 GB of VRAM at 8k context, so 8 GB is insufficient.
Does this model support vision?
No, the model has no vision capabilities.
What is the active parameter count?
By default 2 experts are active, giving about 5B active parameters; up to 4 experts can be activated for ~9B.