TomGrc FusionNet 7Bx2 MoE v0.1 iMat needs about 7.2 GB of memory at Q3_K_S (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 8 quants, from 4.4 GB (Q2_K_S) to 13.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
TomGrc FusionNet 7Bx2 MoE v0.1 iMat is a 12.9B-parameter Tomgrc model in GGUF format, quantized by Nexesenex. Its trained context length is 32K tokens. The repository has 8 quant files, from 4.4 GB (Q2_K_S) to 13.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_S | 4.4 GB | 6.0 GB | Fits | Get file → | |
| Q2_K | 4.8 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q3_K_S | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q3_K_M | 6.2 GB | 7.8 GB | Tight | Get file → | |
| Q4_K_S | 7.3 GB | 8.9 GB | Too big | Get file → | |
| Q5_K_S | 8.9 GB | 10.4 GB | Too big | Get file → | |
| Q8_0 | 13.7 GB | 15.3 GB | Too big | Get file → |
What GPU do you need for TomGrc FusionNet 7Bx2 MoE v0.1 iMat?
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: the best quant that fits is Q2_K_S (4.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_M (6.2 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_S (8.9 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 15.3 GB in use).
Which TomGrc FusionNet 7Bx2 MoE v0.1 iMat quant should you choose?
Q3_K_S (5.6 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K_S at 4.4 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
Frequently asked questions about TomGrc FusionNet 7Bx2 MoE v0.1 iMat
How much VRAM does TomGrc FusionNet 7Bx2 MoE v0.1 iMat need?
About 7.2 GB at Q3_K_S with an 8K context window. That is the 5.6 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 TomGrc FusionNet 7Bx2 MoE v0.1 iMat on an 8 GB GPU?
Yes, with Q3_K_M: the 6.2 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 TomGrc FusionNet 7Bx2 MoE v0.1 iMat GGUF?
It depends on the quant: Q2_K_S is 4.4 GB, Q2_K is 4.8 GB, Q3_K_XS is 5.2 GB, Q3_K_S is 5.6 GB, Q3_K_M is 6.2 GB, Q4_K_S is 7.3 GB and 2 more.
What context length does TomGrc FusionNet 7Bx2 MoE v0.1 iMat 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 TomGrc FusionNet 7Bx2 MoE v0.1 iMat GGUF?
The files are on Hugging Face in the Nexesenex/TomGrc_FusionNet_7Bx2_MoE_v0.1-iMat.GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.