SO

SOLAR 2x10.7B truthy dpo

SolarGGUF by macadelicccUpdated 2024-01-27
Download on Hugging Face
Parameters19.2B
Context4K
Layers48
Architecturellama
Smallest quant7.1 GB
Quick answer

SOLAR 2x10.7B truthy dpo needs about 11.3 GB of memory at Q3_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 7.1 GB (Q2_K) to 10.8 GB (Q4_0).

SOLAR 2x10.7B truthy dpo is a 19.2B-parameter Solar model in GGUF format, quantized by macadeliccc. Its trained context length is 4K tokens. The repository has 3 quant files, from 7.1 GB (Q2_K) to 10.8 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K7.1 GB 8.4 GB
Too big Get file →
Q3_K_M9.2 GB 10.5 GB
Too big Get file →
Q4_010.8 GB 12.1 GB
Too big Get file →

What GPU do you need for SOLAR 2x10.7B truthy dpo?

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 Q3_K_M (9.2 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_0 (10.8 GB file, about 12.9 GB in use).

Which SOLAR 2x10.7B truthy dpo quant should you choose?

Q3_K_M (9.2 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 7.1 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

Architecturellama
Parameters19.2B (approximate, mixture of experts)
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymacadeliccc
FamilySolar
Downloads (HF)22
Last updated2024-01-27

Frequently asked questions about SOLAR 2x10.7B truthy dpo

How much VRAM does SOLAR 2x10.7B truthy dpo need?

About 11.3 GB at Q3_K_M with an 8K context window. That is the 9.2 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 SOLAR 2x10.7B truthy dpo on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SOLAR 2x10.7B truthy dpo GGUF?

It depends on the quant: Q2_K is 7.1 GB, Q3_K_M is 9.2 GB, Q4_0 is 10.8 GB.

What context length does SOLAR 2x10.7B truthy dpo support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download SOLAR 2x10.7B truthy dpo GGUF?

The files are on Hugging Face in the macadeliccc/SOLAR-2x10.7B-truthy-dpo-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from macadeliccc

All by macadeliccc →

More Solar models

All Solar →

Other medium models

All medium models →