mattshumer Reflection Llama 3.1 70B ep2 working needs about 32.5 GB of memory at IQ3_XS (a 29.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 26.4 GB (Q2_K) to 30.9 GB (IQ3_S). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
mattshumer Reflection Llama 3.1 70B ep2 working is a 70.6B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 3 quant files, from 26.4 GB (Q2_K) to 30.9 GB (IQ3_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 26.4 GB | 29.6 GB | Too big | Get file → | |
| IQ3_XS | 29.3 GB | 32.5 GB | Too big | Get file → | |
| IQ3_S | 30.9 GB | 34.1 GB | Too big | Get file → |
What GPU do you need for mattshumer Reflection Llama 3.1 70B ep2 working?
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 Q2_K (26.4 GB file, about 29.6 GB in use).
- 48 GB VRAM: the best quant that fits is IQ3_S (30.9 GB file, about 34.1 GB in use).
Which mattshumer Reflection Llama 3.1 70B ep2 working quant should you choose?
IQ3_XS (29.3 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 at 26.4 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 mattshumer Reflection Llama 3.1 70B ep2 working
How much VRAM does mattshumer Reflection Llama 3.1 70B ep2 working need?
About 32.5 GB at IQ3_XS with an 8K context window. That is the 29.3 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 mattshumer Reflection Llama 3.1 70B ep2 working on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of mattshumer Reflection Llama 3.1 70B ep2 working GGUF?
It depends on the quant: Q2_K is 26.4 GB, IQ3_XS is 29.3 GB, IQ3_S is 30.9 GB.
What context length does mattshumer Reflection Llama 3.1 70B ep2 working support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download mattshumer Reflection Llama 3.1 70B ep2 working GGUF?
The files are on Hugging Face in the RichardErkhov/mattshumer_-_Reflection-Llama-3.1-70B-ep2-working-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 mattshumer Reflection Llama 3.1 70B ep2 working use?
Hugging Face lists the license as llama3.1. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.