SO

SOLARC MOE 10.7Bx6 i1

SolarcGGUF by mradermacherUpdated 2024-11-03
Download on Hugging Face
Parameters53B
Context4K
Layers48
Architecturellama
Smallest quant10.8 GB
Quick answer

SOLARC MOE 10.7Bx6 i1 needs about 34.2 GB of memory at Q4_K_M (a 32.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 10.8 GB (IQ1_S) to 43.5 GB (Q6_K).

SOLARC MOE 10.7Bx6 i1 is a 53B-parameter Solarc model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 21 quant files, from 10.8 GB (IQ1_S) to 43.5 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S10.8 GB 12.2 GB
Too big Get file →
IQ1_M12.0 GB 13.3 GB
Too big Get file →
IQ2_XXS13.9 GB 15.3 GB
Too big Get file →
IQ2_XS15.5 GB 16.8 GB
Too big Get file →
IQ2_S15.9 GB 17.2 GB
Too big Get file →
IQ2_M17.4 GB 18.7 GB
Too big Get file →
Q2_K19.3 GB 20.6 GB
Too big Get file →
IQ3_XXS20.4 GB 21.7 GB
Too big Get file →
IQ3_XS21.6 GB 22.9 GB
Too big Get file →
Q3_K_S22.8 GB 24.1 GB
Too big Get file →
IQ3_S22.9 GB 24.2 GB
Too big Get file →
IQ3_M23.3 GB 24.6 GB
Too big Get file →
Q3_K_M25.3 GB 26.7 GB
Too big Get file →
Q3_K_L27.5 GB 28.8 GB
Too big Get file →
IQ4_XS28.2 GB 29.5 GB
Too big Get file →
Q4_030.0 GB 31.3 GB
Too big Get file →
Q4_K_S30.1 GB 31.4 GB
Too big Get file →
Q4_K_M32.1 GB 33.4 GB
Too big Get file →
Q5_K_S36.5 GB 37.8 GB
Too big Get file →
Q5_K_M37.6 GB 38.9 GB
Too big Get file →
Q6_K43.5 GB 44.8 GB
Too big Get file →

What GPU do you need for SOLARC MOE 10.7Bx6 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: 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 IQ1_M (12.0 GB file, about 14.1 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_XS (21.6 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ4_XS (28.2 GB file, about 30.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (43.5 GB file, about 45.6 GB in use).

Which SOLARC MOE 10.7Bx6 i1 quant should you choose?

Q4_K_M is the usual starting point for SOLARC MOE 10.7Bx6 i1: it balances file size and quality well. Here it is a 32.1 GB file.

If memory is tight, the smallest file is IQ1_S at 10.8 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
Parameters53B (approximate, mixture of experts)
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilySolarc
Downloads (HF)278
Last updated2024-11-03

Frequently asked questions about SOLARC MOE 10.7Bx6 i1

How much VRAM does SOLARC MOE 10.7Bx6 i1 need?

About 34.2 GB at Q4_K_M with an 8K context window. That is the 32.1 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 SOLARC MOE 10.7Bx6 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SOLARC MOE 10.7Bx6 i1 GGUF?

It depends on the quant: IQ1_S is 10.8 GB, IQ1_M is 12.0 GB, IQ2_XXS is 13.9 GB, IQ2_XS is 15.5 GB, IQ2_S is 15.9 GB, IQ2_M is 17.4 GB and 15 more.

What context length does SOLARC MOE 10.7Bx6 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 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download SOLARC MOE 10.7Bx6 i1 GGUF?

The files are on Hugging Face in the mradermacher/SOLARC-MOE-10.7Bx6-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 SOLARC MOE 10.7Bx6 i1 use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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 SOLARC-MOE-10.7Bx6

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Solarc models

All Solarc →

Other large models

All large models →