Threnystril 2x7B moe needs about 9.5 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 16 quants, from 4.9 GB (Q2_K) to 13.8 GB (Q8_0).
Threnystril 2x7B moe – 12.9B parameter Llama model
Threnystril 2x7B moe is a 12.9B parameter Llama architecture model. It supports a 8192 token context window and is released under the apache-2.0 license. The model is a mixture of experts with no vision capability.
Good at
- Large context generation
- High token throughput
- Versatile language support
Limits
- Requires 8k context for full performance
- No vision support
- Mixture of experts may increase memory usage
Best for
- Chatbot development
- Content generation
- Research prototyping
Who it’s for. Developers and researchers needing a large Llama model with a 8192 token context window. Suitable for applications that can accommodate the memory demands of a 12.9B parameter mixture of experts model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.9 GB | 6.5 GB | Fits | Get file → | |
| IQ3_XS | 5.5 GB | 7.0 GB | Fits | Get file → | |
| Q3_K_S | 5.7 GB | 7.3 GB | Tight | Get file → | |
| IQ3_S | 5.8 GB | 7.3 GB | Tight | Get file → | |
| IQ3_M | 5.9 GB | 7.5 GB | Tight | Get file → | |
| Q3_K_M | 6.4 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_L | 6.9 GB | 8.5 GB | Too big | Get file → | |
| IQ4_XS | 7.1 GB | 8.7 GB | Too big | Get file → | |
| Q4_0 | 7.4 GB | 9.0 GB | Too big | Get file → | |
| Q4_K_S | 7.5 GB | 9.1 GB | Too big | Get file → | |
| IQ4_NL | 7.5 GB | 9.1 GB | Too big | Get file → | |
| Q4_K_M | 7.9 GB | 9.5 GB | Too big | Get file → | |
| Q5_K_S | 9.0 GB | 10.6 GB | Too big | Get file → | |
| Q5_K_M | 9.3 GB | 10.9 GB | Too big | Get file → | |
| Q6_K | 10.7 GB | 12.3 GB | Too big | Get file → | |
| Q8_0 | 13.8 GB | 15.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (file size 4.91 GB, estimated memory 6.5 GB). For 12 GB VRAM, Q4_K_M (file size 7.94 GB, estimated memory 9.5 GB). For 16 GB VRAM, Q5_K_M (file size 9.29 GB, estimated memory 10.9 GB).
What GPU do you need for Threnystril 2x7B moe?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q3_K_M (6.4 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (9.3 GB file, about 10.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 15.4 GB in use).
Which Threnystril 2x7B moe quant should you choose?
Q4_K_M is the usual starting point for Threnystril 2x7B moe: it balances file size and quality well. Here it is a 7.9 GB file.
The Q8_0 file is 13.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 4.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Threnystril 2x7B moe
How much VRAM does Threnystril 2x7B moe need?
About 9.5 GB at Q4_K_M with an 8K context window. That is the 7.9 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 Threnystril 2x7B moe on an 8 GB GPU?
Yes, with Q3_K_M: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Threnystril 2x7B moe GGUF?
It depends on the quant: Q2_K is 4.9 GB, IQ3_XS is 5.5 GB, Q3_K_S is 5.7 GB, IQ3_S is 5.8 GB, IQ3_M is 5.9 GB, Q3_K_M is 6.4 GB and 10 more.
What context length does Threnystril 2x7B moe support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download Threnystril 2x7B moe GGUF?
The files are on Hugging Face in the mradermacher/Threnystril-2x7B-moe-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 Threnystril 2x7B moe 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 Threnystril 2x7B moe on 8 GB VRAM?
Yes, the Q2_K quant uses about 6.5 GB of VRAM at 8k context, which fits within 8 GB.
Does this model support vision tasks?
No, the model has no vision capability.
What license applies to this model?
The model is released under the apache-2.0 license.