SO

SOLAR 13B Instruct v1.0

SolarGGUF by mradermacherUpdated 2024-11-28
Download on Hugging Face
Parameters12.5B
Context4K
Layers56
Architecturellama
Smallest quant4.6 GB
Quick answer

SOLAR 13B Instruct v1.0 needs about 9.9 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 4.6 GB (Q2_K) to 13.3 GB (Q8_0).

SOLAR 13B Instruct v1.0 – a 13‑billion‑parameter instruction model in GGUF format

SOLAR 13B Instruct v1.0 is a 12.5‑billion‑parameter model based on the Solar family and the llama architecture. It supports a 4096‑token context window and is distributed under the apache-2.0 license. The model is available in multiple static quantizations for efficient GPU deployment.

Good at

  • Instruction following
  • Long‑form text generation
  • Multilingual support

Limits

  • No vision capabilities
  • Requires 8‑k context for memory estimates
  • License is apache-2.0

Best for

  • Chatbots needing instruction compliance
  • Content drafting with long context
  • Fine‑tuning on custom datasets

Who it’s for. Developers and researchers who need a large instruction‑tuned model that can run on consumer GPUs. The model is suitable for local deployment with GGUF and llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.6 GB 6.1 GB
Fits Get file →
Q3_K_S5.4 GB 6.9 GB
Fits Get file →
Q3_K_M6.0 GB 7.5 GB
Tight Get file →
Q3_K_L6.6 GB 8.0 GB
Too big Get file →
IQ4_XS6.8 GB 8.2 GB
Too big Get file →
Q4_07.1 GB 8.5 GB
Too big Get file →
Q4_K_S7.1 GB 8.5 GB
Too big Get file →
Q4_K_M7.5 GB 8.9 GB
Too big Get file →
Q5_K_S8.6 GB 10.0 GB
Too big Get file →
Q5_K_M8.8 GB 10.3 GB
Too big Get file →
Q6_K10.2 GB 11.7 GB
Too big Get file →
Q8_013.3 GB 14.7 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 4.65 GB, estimated 7 GB memory at 8 k context). If more VRAM is available, Q3_K_S (5.41 GB, 7.8 GB memory) or Q3_K_M (6.03 GB, 8.4 GB memory) provide better quality. For 12 GB VRAM, Q4_K_M (7.51 GB, 9.9 GB memory) is a good balance between size and performance.

What GPU do you need for SOLAR 13B Instruct v1.0?

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 Q3_K_S (5.4 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (8.8 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.3 GB file, about 15.6 GB in use).

Which SOLAR 13B Instruct v1.0 quant should you choose?

Q4_K_M is the usual starting point for SOLAR 13B Instruct v1.0: it balances file size and quality well. Here it is a 7.5 GB file.

The Q8_0 file is 13.3 GB, about 1.8 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 4.6 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
Parameters12.5B
Layers56
Trained context4,096 tokens
KV cache (fp16)224 KB per token

Source

Quantized bymradermacher
FamilySolar
Licenseapache-2.0
Downloads (HF)656
Last updated2024-11-28

Frequently asked questions about SOLAR 13B Instruct v1.0

How much VRAM does SOLAR 13B Instruct v1.0 need?

About 9.9 GB at Q4_K_M with an 8K context window. That is the 7.5 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 13B Instruct v1.0 on an 8 GB GPU?

Yes, with Q3_K_S: the 5.4 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SOLAR 13B Instruct v1.0 GGUF?

It depends on the quant: Q2_K is 4.6 GB, Q3_K_S is 5.4 GB, Q3_K_M is 6.0 GB, Q3_K_L is 6.6 GB, IQ4_XS is 6.8 GB, Q4_0 is 7.1 GB and 6 more.

What context length does SOLAR 13B Instruct v1.0 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.9 GB at 8K and 0.9 GB at 4K.

Where can I download SOLAR 13B Instruct v1.0 GGUF?

The files are on Hugging Face in the mradermacher/SOLAR-13B-Instruct-v1.0-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 SOLAR 13B Instruct v1.0 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.

Can I run SOLAR 13B Instruct on a GPU with 8 GB VRAM?

Yes, the Q2_K quantization requires approximately 7 GB of VRAM at 8 k context, which fits within an 8 GB GPU. Other quants may exceed the limit.

Does this model support vision tasks?

No, SOLAR 13B Instruct does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of SOLAR-13B-Instruct-v1.0

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Solar models

All Solar →

Other medium models

All medium models →