Endurance 100B v1 needs about 62.9 GB of memory at Q4_K_M (a 60.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 23.3 GB (IQ1_M) to 106.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 9.7 GB.
Endurance 100B v1 is a 100B-parameter Endurance model in GGUF format, quantized by bartowski. Its trained context length is 128K tokens. The repository has 24 quant files, from 23.3 GB (IQ1_M) to 106.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 23.3 GB | 26.2 GB | Too big | Get file → | |
| IQ2_XXS | 26.6 GB | 29.5 GB | Too big | Get file → | |
| IQ2_XS | 29.6 GB | 32.5 GB | Too big | Get file → | |
| IQ2_M | 34.1 GB | 37.1 GB | Too big | Get file → | |
| Q2_K | 37.1 GB | 40.0 GB | Too big | Get file → | |
| Q2_K_L | 37.5 GB | 40.4 GB | Too big | Get file → | |
| IQ3_XXS | 38.5 GB | 41.5 GB | Too big | Get file → | |
| Q3_K_S | 43.3 GB | 46.2 GB | Too big | Get file → | |
| IQ3_M | 45.3 GB | 48.2 GB | Too big | Get file → | |
| Q3_K_M | 48.4 GB | 51.4 GB | Too big | Get file → | |
| Q3_K_L | 52.9 GB (2 parts) | 55.8 GB | Too big | Get file → | |
| Q3_K_XL | 53.3 GB (2 parts) | 56.2 GB | Too big | Get file → | |
| IQ4_XS | 53.6 GB (2 parts) | 56.6 GB | Too big | Get file → | |
| Q4_0 | 56.6 GB (2 parts) | 59.5 GB | Too big | Get file → | |
| Q4_0 | 56.6 GB (2 parts) | 59.5 GB | Too big | Get file → | |
| Q4_0 | 56.6 GB (2 parts) | 59.5 GB | Too big | Get file → | |
| IQ4_NL | 56.7 GB (2 parts) | 59.7 GB | Too big | Get file → | |
| Q4_0 | 56.8 GB (2 parts) | 59.7 GB | Too big | Get file → | |
| Q4_K_S | 57.0 GB (2 parts) | 59.9 GB | Too big | Get file → | |
| Q4_K_M | 60.0 GB (2 parts) | 62.9 GB | Too big | Get file → | |
| Q5_K_S | 69.1 GB (2 parts) | 72.0 GB | Too big | Get file → | |
| Q5_K_M | 70.9 GB (2 parts) | 73.8 GB | Too big | Get file → | |
| Q6_K | 82.4 GB (3 parts) | 85.3 GB | Too big | Get file → | |
| Q8_0 | 106.7 GB (3 parts) | 109.7 GB | Too big | Get file → |
What GPU do you need for Endurance 100B v1?
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 (26.6 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q3_K_S (43.3 GB file, about 46.2 GB in use).
Which Endurance 100B v1 quant should you choose?
Q4_K_M is the usual starting point for Endurance 100B v1: it balances file size and quality well. Here it is a 60.0 GB file.
The Q8_0 file is 106.7 GB, about 1.8 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 IQ1_M at 23.3 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
Source
Frequently asked questions about Endurance 100B v1
How much VRAM does Endurance 100B v1 need?
About 62.9 GB at Q4_K_M with an 8K context window. That is the 60.0 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 Endurance 100B v1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Endurance 100B v1 GGUF?
It depends on the quant: IQ1_M is 23.3 GB, IQ2_XXS is 26.6 GB, IQ2_XS is 29.6 GB, IQ2_M is 34.1 GB, Q2_K is 37.1 GB, Q2_K_L is 37.5 GB and 18 more.
What context length does Endurance 100B v1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.4 GB at 8K and 9.7 GB at 32K.
Where can I download Endurance 100B v1 GGUF?
The files are on Hugging Face in the bartowski/Endurance-100B-v1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.