FR

franken SOLAR 18B v1.0 i1

FrankenGGUF by mradermacherUpdated 2024-11-28
Download on Hugging Face
Parameters17.9B
Context4K
Layers81
Architecturellama
Smallest quant3.9 GB
Quick answer

franken SOLAR 18B v1.0 i1 needs about 14.0 GB of memory at Q4_K_M (a 10.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 3.9 GB (IQ1_S) to 14.7 GB (Q6_K).

franken SOLAR 18B v1.0 i1 is a 17.9B-parameter Franken model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 21 quant files, from 3.9 GB (IQ1_S) to 14.7 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.9 GB 5.7 GB
Fits Get file →
IQ1_M4.2 GB 6.1 GB
Fits Get file →
IQ2_XXS4.8 GB 6.7 GB
Fits Get file →
IQ2_XS5.4 GB 7.2 GB
Tight Get file →
IQ2_S5.6 GB 7.5 GB
Tight Get file →
IQ2_M6.1 GB 8.0 GB
Tight Get file →
Q2_K6.7 GB 8.5 GB
Too big Get file →
IQ3_XXS6.9 GB 8.8 GB
Too big Get file →
IQ3_XS7.4 GB 9.3 GB
Too big Get file →
Q3_K_S7.8 GB 9.6 GB
Too big Get file →
IQ3_S7.8 GB 9.7 GB
Too big Get file →
IQ3_M8.1 GB 9.9 GB
Too big Get file →
Q3_K_M8.7 GB 10.5 GB
Too big Get file →
Q3_K_L9.4 GB 11.3 GB
Too big Get file →
IQ4_XS9.6 GB 11.5 GB
Too big Get file →
Q4_010.2 GB 12.0 GB
Too big Get file →
Q4_K_S10.2 GB 12.1 GB
Too big Get file →
Q4_K_M10.8 GB 12.6 GB
Too big Get file →
Q5_K_S12.3 GB 14.2 GB
Too big Get file →
Q5_K_M12.7 GB 14.5 GB
Too big Get file →
Q6_K14.7 GB 16.6 GB
Too big Get file →

What GPU do you need for franken SOLAR 18B v1.0 i1?

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: the best quant that fits is IQ1_M (4.2 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q3_K_M (8.7 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (12.7 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (14.7 GB file, about 17.9 GB in use).

Which franken SOLAR 18B v1.0 i1 quant should you choose?

Q4_K_M is the usual starting point for franken SOLAR 18B v1.0 i1: it balances file size and quality well. Here it is a 10.8 GB file.

If memory is tight, the smallest file is IQ1_S at 3.9 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
Parameters17.9B
Layers81
Trained context4,096 tokens
KV cache (fp16)324 KB per token

Source

Quantized bymradermacher
FamilyFranken
Licenseapache-2.0
Downloads (HF)233
Last updated2024-11-28

Frequently asked questions about franken SOLAR 18B v1.0 i1

How much VRAM does franken SOLAR 18B v1.0 i1 need?

About 14.0 GB at Q4_K_M with an 8K context window. That is the 10.8 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 franken SOLAR 18B v1.0 i1 on an 8 GB GPU?

Yes, with IQ1_M: the 4.2 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of franken SOLAR 18B v1.0 i1 GGUF?

It depends on the quant: IQ1_S is 3.9 GB, IQ1_M is 4.2 GB, IQ2_XXS is 4.8 GB, IQ2_XS is 5.4 GB, IQ2_S is 5.6 GB, IQ2_M is 6.1 GB and 15 more.

What context length does franken SOLAR 18B v1.0 i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.4 GB at 4K.

Where can I download franken SOLAR 18B v1.0 i1 GGUF?

The files are on Hugging Face in the mradermacher/franken-SOLAR-18B-v1.0-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does franken SOLAR 18B v1.0 i1 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of franken-SOLAR-18B-v1.0

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Franken models

All Franken →

Other medium models

All medium models →