SO

SOLAR math 2x10.7b v0.2

SolarGGUF by macadelicccUpdated 2024-01-18
Download on Hugging Face
Parameters19.2B
Context4K
Layers48
Architecturellama
Smallest quant11.6 GB
Quick answer

SOLAR math 2x10.7b v0.2 needs about 13.7 GB of memory at Q4_K_M (a 11.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 11.6 GB (Q4_K_M) to 13.6 GB (Q5_K_M).

SOLAR math 2x10.7b v0.2 is a 19.2B-parameter Solar model in GGUF format, quantized by macadeliccc. Its trained context length is 4K tokens. The repository has 2 quant files, from 11.6 GB (Q4_K_M) to 13.6 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M11.6 GB 12.9 GB
Too big Get file →
Q5_K_M13.6 GB 14.9 GB
Too big Get file →

What GPU do you need for SOLAR math 2x10.7b v0.2?

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: the best quant that fits is Q5_K_M (13.6 GB file, about 15.7 GB in use).

Which SOLAR math 2x10.7b v0.2 quant should you choose?

Q4_K_M is the usual starting point for SOLAR math 2x10.7b v0.2: it balances file size and quality well. Here it is a 11.6 GB file.

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)18
Last updated2024-01-18

Frequently asked questions about SOLAR math 2x10.7b v0.2

How much VRAM does SOLAR math 2x10.7b v0.2 need?

About 13.7 GB at Q4_K_M with an 8K context window. That is the 11.6 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 math 2x10.7b v0.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SOLAR math 2x10.7b v0.2 GGUF?

It depends on the quant: Q4_K_M is 11.6 GB, Q5_K_M is 13.6 GB.

What context length does SOLAR math 2x10.7b v0.2 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 math 2x10.7b v0.2 GGUF?

The files are on Hugging Face in the macadeliccc/SOLAR-math-2x10.7b-v0.2-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 →