Llama 3 Peach Instruct 4x8B MoE needs about 16.7 GB of memory at Q4_K_M (a 15.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 18 quants, from 9.3 GB (Q2_K) to 49.9 GB (F16).
Llama 3 Peach Instruct 4x8B MoE – a 24.9B parameter mixture of experts model
Llama 3 Peach Instruct 4x8B MoE is a 24.9B parameter model built as a mixture of experts. It was created by merging four 8B Llama 3 instruct models. The model supports a 8192 token context window.
Good at
- Large context handling
- Mixture of expert specialization
- Instruction following
Limits
- No license information provided
- No vision support
- Requires significant VRAM for higher quantizations
Best for
- Chat applications needing 8k context
- Fine‑tuning on custom instruction datasets
- Research on MoE architectures
Who it’s for. Developers and researchers who need a large‑parameter Llama 3 model with expert specialization and a long context window. The model is suitable for advanced chatbots and instruction‑driven tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 9.3 GB | 10.9 GB | Too big | Get file → | |
| Q3_K_S | 10.9 GB | 12.5 GB | Too big | Get file → | |
| Q3_K | 12.1 GB | 13.7 GB | Too big | Get file → | |
| Q3_K_M | 12.1 GB | 13.7 GB | Too big | Get file → | |
| Q3_K_L | 13.0 GB | 14.6 GB | Too big | Get file → | |
| Q4_0 | 14.2 GB | 15.7 GB | Too big | Get file → | |
| Q4_K_S | 14.3 GB | 15.9 GB | Too big | Get file → | |
| Q4_K | 15.2 GB | 16.7 GB | Too big | Get file → | |
| Q4_K_M | 15.2 GB | 16.7 GB | Too big | Get file → | |
| Q4_1 | 15.7 GB | 17.3 GB | Too big | Get file → | |
| Q5_0 | 17.2 GB | 18.8 GB | Too big | Get file → | |
| Q5_K_S | 17.2 GB | 18.8 GB | Too big | Get file → | |
| Q5_K | 17.7 GB | 19.3 GB | Too big | Get file → | |
| Q5_K_M | 17.7 GB | 19.3 GB | Too big | Get file → | |
| Q5_1 | 18.8 GB | 20.3 GB | Too big | Get file → | |
| Q6_K | 20.5 GB | 22.0 GB | Too big | Get file → | |
| Q8_0 | 26.5 GB | 28.1 GB | Too big | Get file → | |
| F16 | 49.9 GB | 51.5 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 15.16 GB, estimated memory 16.7 GB). For 12 GB VRAM use Q5_K (file size 17.74 GB, estimated memory 19.3 GB). For 16 GB VRAM use Q6_K (file size 20.47 GB, estimated memory 22 GB). Memory estimates are approximate.
What GPU do you need for Llama 3 Peach Instruct 4x8B 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: the best quant that fits is Q2_K (9.3 GB file, about 10.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (14.3 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (20.5 GB file, about 22.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (26.5 GB file, about 28.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (26.5 GB file, about 28.1 GB in use).
Which Llama 3 Peach Instruct 4x8B MoE quant should you choose?
Q4_K_M is the usual starting point for Llama 3 Peach Instruct 4x8B MoE: it balances file size and quality well. Here it is a 15.2 GB file.
The Q8_0 file is 26.5 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 9.3 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 Llama 3 Peach Instruct 4x8B MoE
How much VRAM does Llama 3 Peach Instruct 4x8B MoE need?
About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.2 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 Llama 3 Peach Instruct 4x8B MoE on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 3 Peach Instruct 4x8B MoE GGUF?
It depends on the quant: Q2_K is 9.3 GB, Q3_K_S is 10.9 GB, Q3_K is 12.1 GB, Q3_K_M is 12.1 GB, Q3_K_L is 13.0 GB, Q4_0 is 14.2 GB and 12 more.
What context length does Llama 3 Peach Instruct 4x8B 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 Llama 3 Peach Instruct 4x8B MoE GGUF?
The files are on Hugging Face in the RDson/Llama-3-Peach-Instruct-4x8B-MoE-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Llama 3 Peach Instruct 4x8B MoE on 8 GB VRAM?
The Q4_K_M quantization requires about 16.7 GB VRAM, so 8 GB VRAM is insufficient.
Does this model support vision tasks?
No, the model has no vision capabilities.
What is the context length of this model?
The model supports a 8192 token context window.