SO

SOLAR 13B Instruct v1.0 i1

SolarGGUF by mradermacherUpdated 2024-11-28
Download on Hugging Face
Parameters12.5B
Context4K
Layers56
Architecturellama
Smallest quant2.7 GB
Quick answer

SOLAR 13B Instruct v1.0 i1 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 24 quants, from 2.7 GB (IQ1_S) to 10.2 GB (Q6_K).

SOLAR 13B Instruct v1.0 i1 – a 13B instruction‑tuned LLM in GGUF format

SOLAR 13B Instruct v1.0 i1 is a 12.5B‑parameter model based on the Solar family. It is optimized for VRAM usage on typical GPUs, with a 4‑bit quant fitting in 12GB. The model supports a 4096‑token context window and is released under Apache‑2.0.

Good at

  • Instruction following
  • Long‑form text generation
  • Contextual reasoning

Limits

  • No vision support
  • Requires 4096‑token context
  • No external knowledge beyond training

Best for

  • Chatbots on mid‑range GPUs
  • Fine‑tuning on custom datasets
  • Rapid prototyping of instruction‑based LLMs

Who it’s for. Developers and researchers who need a 13B instruction‑tuned model that runs efficiently on consumer GPUs. The model is suitable for applications requiring a 4096‑token context and no vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.7 GB 4.2 GB
Fits Get file →
IQ1_M3.0 GB 4.4 GB
Fits Get file →
IQ2_XXS3.4 GB 4.8 GB
Fits Get file →
IQ2_XS3.7 GB 5.2 GB
Fits Get file →
IQ2_S3.9 GB 5.4 GB
Fits Get file →
IQ2_M4.3 GB 5.7 GB
Fits Get file →
Q2_K4.6 GB 6.1 GB
Fits Get file →
IQ3_XXS4.8 GB 6.3 GB
Fits Get file →
IQ3_XS5.2 GB 6.6 GB
Fits Get file →
Q3_K_S5.4 GB 6.9 GB
Fits Get file →
IQ3_S5.4 GB 6.9 GB
Fits Get file →
IQ3_M5.6 GB 7.1 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_XS6.7 GB 8.1 GB
Too big Get file →
Q4_07.1 GB 8.5 GB
Too big Get file →
Q4_07.1 GB 8.5 GB
Too big Get file →
Q4_07.1 GB 8.5 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 →

For 8GB VRAM, use IQ1_S (file size 2.72 GB, estimated 5.1 GB memory at 8k context) or IQ1_M (2.97 GB, 5.3 GB). For 12GB VRAM, IQ4_0 (7.05 GB, 9.4 GB) or Q4_K_M (7.51 GB, 9.9 GB) are suitable. Larger VRAM allows higher‑quality quants such as Q5_K_M (8.83 GB, 11.2 GB).

What GPU do you need for SOLAR 13B Instruct 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: the best quant that fits is IQ2_XXS (3.4 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_M (5.6 GB file, about 8.0 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 Q6_K (10.2 GB file, about 12.6 GB in use).

Which SOLAR 13B Instruct v1.0 i1 quant should you choose?

Q4_K_M is the usual starting point for SOLAR 13B Instruct v1.0 i1: it balances file size and quality well. Here it is a 7.5 GB file.

If memory is tight, the smallest file is IQ1_S at 2.7 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)862
Last updated2024-11-28

Frequently asked questions about SOLAR 13B Instruct v1.0 i1

How much VRAM does SOLAR 13B Instruct v1.0 i1 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 i1 on an 8 GB GPU?

Yes, with IQ3_M: the 5.6 GB file needs about 8.0 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 i1 GGUF?

It depends on the quant: IQ1_S is 2.7 GB, IQ1_M is 3.0 GB, IQ2_XXS is 3.4 GB, IQ2_XS is 3.7 GB, IQ2_S is 3.9 GB, IQ2_M is 4.3 GB and 18 more.

What context length does SOLAR 13B Instruct 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 1.9 GB at 8K and 0.9 GB at 4K.

Where can I download SOLAR 13B Instruct v1.0 i1 GGUF?

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

Can I run this model on 8GB VRAM?

Yes, use IQ1_S or IQ1_M quant, which fit within 8GB VRAM and use about 5.1–5.3GB of memory at 8k context.

Does the model support vision tasks?

No, the model has no vision capabilities and is purely text‑based.

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 →