jondurbin bagel 8x7b v0.2 needs about 4.8 GB of memory at Q4_K_M (a 3.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 22 quants, from 3.9 GB (Q4_K_M) to 49.6 GB (Q8_0).
jondurbin bagel 8x7b v0.2 is a 46.7B-parameter Jondurbin model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 3.9 GB (Q4_K_M) to 49.6 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 3.9 GB | 4.8 GB | Fits | Get file → | |
| Q4_0 | 6.1 GB | 7.3 GB | Tight | Get file → | |
| IQ4_XS | 12.5 GB | 14.5 GB | Too big | Get file → | |
| Q2_K | 17.3 GB | 19.9 GB | Too big | Get file → | |
| IQ3_XS | 19.4 GB | 22.2 GB | Too big | Get file → | |
| IQ3_S | 20.4 GB | 23.4 GB | Too big | Get file → | |
| Q3_K_S | 20.4 GB | 23.4 GB | Too big | Get file → | |
| IQ4_NL | 20.9 GB | 23.9 GB | Too big | Get file → | |
| IQ3_M | 21.4 GB | 24.5 GB | Too big | Get file → | |
| Q3_K | 22.5 GB | 25.8 GB | Too big | Get file → | |
| Q3_K_M | 22.5 GB | 25.8 GB | Too big | Get file → | |
| Q3_K_L | 24.2 GB | 27.6 GB | Too big | Get file → | |
| Q4_K_S | 26.7 GB | 30.5 GB | Too big | Get file → | |
| Q4_K | 28.4 GB | 32.4 GB | Too big | Get file → | |
| Q4_1 | 29.3 GB | 33.4 GB | Too big | Get file → | |
| Q5_0 | 32.2 GB | 36.6 GB | Too big | Get file → | |
| Q5_K_S | 32.2 GB | 36.6 GB | Too big | Get file → | |
| Q5_K | 33.2 GB | 37.7 GB | Too big | Get file → | |
| Q5_K_M | 33.2 GB | 37.7 GB | Too big | Get file → | |
| Q5_1 | 35.1 GB | 39.8 GB | Too big | Get file → | |
| Q6_K | 38.4 GB | 43.5 GB | Too big | Get file → | |
| Q8_0 | 49.6 GB (2 parts) | 56.1 GB | Too big | Get file → |
What GPU do you need for jondurbin bagel 8x7b v0.2?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_K_M (3.9 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_0 (6.1 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_0 (6.1 GB file, about 7.3 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (12.5 GB file, about 14.5 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_NL (20.9 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_S (26.7 GB file, about 30.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 43.5 GB in use).
Which jondurbin bagel 8x7b v0.2 quant should you choose?
Q4_K_M is the usual starting point for jondurbin bagel 8x7b v0.2: it balances file size and quality well. Here it is a 3.9 GB file.
The Q8_0 file is 49.6 GB, about 12.8 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about jondurbin bagel 8x7b v0.2
How much VRAM does jondurbin bagel 8x7b v0.2 need?
About 4.8 GB at Q4_K_M with an 8K context window. That is the 3.9 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 jondurbin bagel 8x7b v0.2 on an 8 GB GPU?
Yes, with Q4_0: the 6.1 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of jondurbin bagel 8x7b v0.2 GGUF?
It depends on the quant: Q4_K_M is 3.9 GB, Q4_0 is 6.1 GB, IQ4_XS is 12.5 GB, Q2_K is 17.3 GB, IQ3_XS is 19.4 GB, IQ3_S is 20.4 GB and 16 more.
What context length does jondurbin bagel 8x7b v0.2 support?
The GGUF header lists a trained context length of 32,768 tokens (32K).
Where can I download jondurbin bagel 8x7b v0.2 GGUF?
The files are on Hugging Face in the RichardErkhov/jondurbin_-_bagel-8x7b-v0.2-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.