Llama 3 Motif 102B Instruct needs about 38.8 GB of memory at Q2_K_S (a 35.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 14 quants, from 22.0 GB (IQ1_S) to 49.3 GB (Q3_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Llama 3 Motif 102B Instruct is a 102B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 14 quant files, from 22.0 GB (IQ1_S) to 49.3 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 22.0 GB | 25.7 GB | Too big | Get file → | |
| IQ1_M | 24.0 GB | 27.7 GB | Too big | Get file → | |
| IQ2_XXS | 27.4 GB | 31.1 GB | Too big | Get file → | |
| IQ2_XS | 30.4 GB | 34.1 GB | Too big | Get file → | |
| IQ2_S | 32.0 GB | 35.7 GB | Too big | Get file → | |
| IQ2_M | 34.7 GB | 38.5 GB | Too big | Get file → | |
| Q2_K_S | 35.1 GB | 38.8 GB | Too big | Get file → | |
| Q2_K | 37.9 GB | 41.6 GB | Too big | Get file → | |
| IQ3_XXS | 39.5 GB | 43.2 GB | Too big | Get file → | |
| IQ3_XS | 42.1 GB | 45.8 GB | Too big | Get file → | |
| Q3_K_S | 44.3 GB | 48.0 GB | Too big | Get file → | |
| IQ3_S | 44.4 GB | 48.2 GB | Too big | Get file → | |
| IQ3_M | 46.0 GB | 49.7 GB | Too big | Get file → | |
| Q3_K_M | 49.3 GB | 53.1 GB | Too big | Get file → |
What GPU do you need for Llama 3 Motif 102B Instruct?
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 IQ2_XXS (27.4 GB file, about 31.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q3_K_S (44.3 GB file, about 48.0 GB in use).
Which Llama 3 Motif 102B Instruct quant should you choose?
Q2_K_S (35.1 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 22.0 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 Llama 3 Motif 102B Instruct
How much VRAM does Llama 3 Motif 102B Instruct need?
About 38.8 GB at Q2_K_S with an 8K context window. That is the 35.1 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 Motif 102B Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 25.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 3 Motif 102B Instruct GGUF?
It depends on the quant: IQ1_S is 22.0 GB, IQ1_M is 24.0 GB, IQ2_XXS is 27.4 GB, IQ2_XS is 30.4 GB, IQ2_S is 32.0 GB, IQ2_M is 34.7 GB and 8 more.
What context length does Llama 3 Motif 102B Instruct support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download Llama 3 Motif 102B Instruct GGUF?
The files are on Hugging Face in the mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.