SO

SOLARC MOE 10.7Bx4

SolarcGGUF by TheBlokeUpdated 2023-12-28
Download on Hugging Face
Parameters36B
Context4K
Layers48
Architecturellama
Smallest quant12.0 GB
Quick answer

SOLARC MOE 10.7Bx4 needs about 22.5 GB of memory at Q4_K_M (a 20.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 12.0 GB (Q2_K) to 38.4 GB (Q8_0).

SOLARC MOE 10.7Bx4 – 36B parameter mixture of experts LLM

SOLARC MOE 10.7Bx4 is a 36B parameter auto‑regressive language model based on the SOLAR architecture. It uses a mixture of experts and supports a 4096 token context window. The model is text‑only and released under a cc‑by‑nc‑sa‑4.0 license.

Good at

  • Large context generation
  • Mixture of experts efficiency
  • Text‑only tasks

Limits

  • No vision support
  • Commercial use restricted by license
  • High VRAM requirement

Best for

  • Chat applications
  • Story generation
  • Research prototyping

Who it’s for. Developers needing a large language model with mixture of experts for text generation. Suitable for non‑commercial projects under cc‑by‑nc‑sa‑4.0.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.0 GB 13.3 GB
Too big Get file →
Q3_K_M15.7 GB 17.0 GB
Too big Get file →
Q4_020.3 GB 21.6 GB
Too big Get file →
Q4_K_M20.4 GB 21.7 GB
Too big Get file →
Q5_024.8 GB 26.1 GB
Too big Get file →
Q5_K_M24.9 GB 26.2 GB
Too big Get file →
Q6_K29.6 GB 30.9 GB
Too big Get file →
Q8_038.4 GB 39.7 GB
Too big Get file →

For 16GB VRAM, use Q4_0 or Q4_K_M (22.5GB estimate). For 32GB VRAM, Q6_K (31.7GB estimate) is suitable. For 40GB VRAM, Q8_0 (40.5GB estimate) provides the highest quality.

What GPU do you need for SOLARC MOE 10.7Bx4?

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 Q2_K (12.0 GB file, about 14.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.4 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.6 GB file, about 31.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (38.4 GB file, about 40.5 GB in use).

Which SOLARC MOE 10.7Bx4 quant should you choose?

Q4_K_M is the usual starting point for SOLARC MOE 10.7Bx4: it balances file size and quality well. Here it is a 20.4 GB file.

The Q8_0 file is 38.4 GB, about 1.9 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.

If memory is tight, the smallest file is Q2_K at 12.0 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
Parameters36B (approximate, mixture of experts)
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized byTheBloke
FamilySolarc
Downloads (HF)1,924
Last updated2023-12-28

Frequently asked questions about SOLARC MOE 10.7Bx4

How much VRAM does SOLARC MOE 10.7Bx4 need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 20.4 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 10.7Bx4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SOLARC MOE 10.7Bx4 GGUF?

It depends on the quant: Q2_K is 12.0 GB, Q3_K_M is 15.7 GB, Q4_0 is 20.3 GB, Q4_K_M is 20.4 GB, Q5_0 is 24.8 GB, Q5_K_M is 24.9 GB and 2 more.

What context length does SOLARC MOE 10.7Bx4 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 10.7Bx4 GGUF?

The files are on Hugging Face in the TheBloke/SOLARC-MOE-10.7Bx4-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 10.7Bx4 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.

Can I run this model on 8GB VRAM?

No, the smallest quant requires 14.1GB estimated VRAM at 8k context.

Does it support vision?

No, the model accepts and generates only text.

Is it free to use?

It is free for non‑commercial use under the cc‑by‑nc‑sa‑4.0 license.

Other GGUFs of SOLARC-MOE-10.7Bx4

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Solarc models

All Solarc →

Other large models

All large models →