tomgrc_fusionnet_34bx2_moe needs about 39.2 GB of memory at Q4_K_M (a 36.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 11 quants, from 22.4 GB (Q2_K) to 49.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
FusionNet 34Bx2 MoE – 60.8B parameter Llama model fine‑tuned with MoE
FusionNet_34Bx2_MoE is a 60.8B parameter Llama model fine‑tuned on English using the Mixture of Experts method. It supports a 32,768 token context window and is released under the MIT license.
Good at
- Large context handling
- MoE fine‑tuning
- English language generation
Limits
- No vision support
- Requires large VRAM for higher quants
- License is MIT (open)
Best for
- Research on MoE architectures
- Long‑form text generation
- Fine‑tuning experiments
Who it’s for. Researchers and developers interested in Mixture of Experts models and large‑context LLMs. The model is suitable for those who can allocate sufficient GPU memory and want to experiment with different quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 22.4 GB | 24.9 GB | Too big | Get file → | |
| Q3_K_S | 26.3 GB | 28.8 GB | Too big | Get file → | |
| Q3_K_M | 29.2 GB | 31.7 GB | Too big | Get file → | |
| Q3_K_L | 31.8 GB | 34.3 GB | Too big | Get file → | |
| Q4_0 | 34.3 GB | 36.8 GB | Too big | Get file → | |
| Q4_K_S | 34.6 GB | 37.1 GB | Too big | Get file → | |
| Q4_K_M | 36.7 GB | 39.2 GB | Too big | Get file → | |
| Q5_0 | 41.9 GB | 44.4 GB | Too big | Get file → | |
| Q5_K_S | 41.9 GB | 44.4 GB | Too big | Get file → | |
| Q5_K_M | 43.1 GB | 45.6 GB | Too big | Get file → | |
| Q6_K | 49.9 GB | 52.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (22.39 GB file, ~24.9 GB memory). For 12 GB VRAM, Q3_K_S (26.32 GB file, ~28.8 GB memory). For 16 GB VRAM, Q4_K_M (36.66 GB file, ~39.2 GB memory).
What GPU do you need for tomgrc_fusionnet_34bx2_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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q3_K_M (29.2 GB file, about 31.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (43.1 GB file, about 45.6 GB in use).
Which tomgrc_fusionnet_34bx2_moe quant should you choose?
Q4_K_M is the usual starting point for tomgrc_fusionnet_34bx2_moe: it balances file size and quality well. Here it is a 36.7 GB file.
If memory is tight, the smallest file is Q2_K at 22.4 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
Source
Frequently asked questions about tomgrc_fusionnet_34bx2_moe
How much VRAM does tomgrc_fusionnet_34bx2_moe need?
About 39.2 GB at Q4_K_M with an 8K context window. That is the 36.7 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_34bx2_moe on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of tomgrc_fusionnet_34bx2_moe GGUF?
It depends on the quant: Q2_K is 22.4 GB, Q3_K_S is 26.3 GB, Q3_K_M is 29.2 GB, Q3_K_L is 31.8 GB, Q4_0 is 34.3 GB, Q4_K_S is 34.6 GB and 5 more.
What context length does tomgrc_fusionnet_34bx2_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 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download tomgrc_fusionnet_34bx2_moe GGUF?
The files are on Hugging Face in the TheBloke/FusionNet_34Bx2_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 tomgrc_fusionnet_34bx2_moe use?
Hugging Face lists the license as mit. 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?
Yes, the Q2_K quantization requires about 24.9 GB of memory at 8 k context, which is beyond 8 GB VRAM. You would need a higher VRAM GPU.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license does this model use?
The model is released under the MIT license.