perlthoughts_falkor-8x7b-moe needs about 28.0 GB of memory at Q4_K_M (a 26.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 8 quants, from 15.6 GB (Q2_K) to 49.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Perlthoughts Falkor 8X7B MoE – 46.7B parameter mixture of experts
The Falkor 8X7B MoE model contains 46.7B parameters and supports a 32768 token context window. It is released under the apache-2.0 license and is available in multiple GGUF quantisations for llama.cpp and compatible clients.
Good at
- Large context handling
- Mixture of experts architecture
- High parameter count
Limits
- No vision support
- Requires large VRAM for higher quants
- Only llama.cpp compatible clients listed
Best for
- Chat and support bots
- Long‑form content generation
- Research prototyping
Who it’s for. Developers and researchers needing a large‑parameter LLM with extended context. The model is suitable for CPU+GPU inference using llama.cpp or compatible libraries.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 15.6 GB | 17.2 GB | Too big | Get file → | |
| Q3_K_M | 20.4 GB | 21.9 GB | Too big | Get file → | |
| Q4_0 | 26.4 GB | 28.0 GB | Too big | Get file → | |
| Q4_K_M | 26.4 GB | 28.0 GB | Too big | Get file → | |
| Q5_0 | 32.2 GB | 33.8 GB | Too big | Get file → | |
| Q5_K_M | 32.2 GB | 33.8 GB | Too big | Get file → | |
| Q6_K | 38.4 GB | 40.0 GB | Too big | Get file → | |
| Q8_0 | 49.6 GB | 51.2 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (15.64 GB file, 17.2 GB memory). For 12 GB VRAM use Q3_K_M (20.36 GB file, 21.9 GB memory). For 16 GB VRAM use Q4_0 or Q4_K_M (26.44 GB file, 28 GB memory).
What GPU do you need for perlthoughts_falkor-8x7b-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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q3_K_M (20.4 GB file, about 21.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_0 (26.4 GB file, about 28.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).
Which perlthoughts_falkor-8x7b-moe quant should you choose?
Q4_K_M is the usual starting point for perlthoughts_falkor-8x7b-moe: it balances file size and quality well. Here it is a 26.4 GB file.
The Q8_0 file is 49.6 GB, about 1.9 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 15.6 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 perlthoughts_falkor-8x7b-moe
How much VRAM does perlthoughts_falkor-8x7b-moe need?
About 28.0 GB at Q4_K_M with an 8K context window. That is the 26.4 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 perlthoughts_falkor-8x7b-moe on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of perlthoughts_falkor-8x7b-moe GGUF?
It depends on the quant: Q2_K is 15.6 GB, Q3_K_M is 20.4 GB, Q4_0 is 26.4 GB, Q4_K_M is 26.4 GB, Q5_0 is 32.2 GB, Q5_K_M is 32.2 GB and 2 more.
What context length does perlthoughts_falkor-8x7b-moe support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download perlthoughts_falkor-8x7b-moe GGUF?
The files are on Hugging Face in the TheBloke/Falkor-8x7B-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 perlthoughts_falkor-8x7b-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 Falkor 8X7B MoE on 8 GB VRAM?
Yes, using the Q2_K quantised model which requires approximately 17.2 GB of VRAM at 8k context.
Does this model support image input?
No, the model has no vision capabilities.
Which clients can run this model?
It works with llama.cpp (from Dec 13), KoboldCpp 1.52+, LM Studio 0.2.9+, and llama-cpp-python 0.2.23+.