MI

Soar Mistral 123b

MistralGGUF by mradermacherUpdated 2025-07-11
Download on Hugging Face
Parameters123B
Context128K
Layers88
Architecturellama
Smallest quant26.0 GB
Quick answer

Soar Mistral 123b needs about 41.8 GB of memory at IQ2_S (a 38.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 26.0 GB (IQ1_S) to 47.0 GB (IQ3_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

Soar Mistral 123b is a 123B-parameter Mistral model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 9 quant files, from 26.0 GB (IQ1_S) to 47.0 GB (IQ3_XXS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S26.0 GB 29.4 GB
Too big Get file →
IQ1_M28.4 GB 31.8 GB
Too big Get file →
IQ2_XXS32.4 GB 35.9 GB
Too big Get file →
IQ2_XS36.1 GB 39.5 GB
Too big Get file →
IQ2_S38.4 GB 41.8 GB
Too big Get file →
Q2_K_S41.6 GB 45.1 GB
Too big Get file →
IQ2_M41.6 GB 45.1 GB
Too big Get file →
Q2_K45.2 GB 48.6 GB
Too big Get file →
IQ3_XXS47.0 GB 50.5 GB
Too big Get file →

What GPU do you need for Soar Mistral 123b?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ1_M (28.4 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_M (41.6 GB file, about 45.1 GB in use).

Which Soar Mistral 123b quant should you choose?

IQ2_S (38.4 GB) is the middle option in this repository. 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.

If memory is tight, the smallest file is IQ1_S at 26.0 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
Parameters123B
Layers88
Trained context131,072 tokens
KV cache (fp16)352 KB per token

Source

Quantized bymradermacher
FamilyMistral
Licenseother
Downloads (HF)263
Last updated2025-07-11

Frequently asked questions about Soar Mistral 123b

How much VRAM does Soar Mistral 123b need?

About 41.8 GB at IQ2_S with an 8K context window. That is the 38.4 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 Soar Mistral 123b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Soar Mistral 123b GGUF?

It depends on the quant: IQ1_S is 26.0 GB, IQ1_M is 28.4 GB, IQ2_XXS is 32.4 GB, IQ2_XS is 36.1 GB, IQ2_S is 38.4 GB, Q2_K_S is 41.6 GB and 3 more.

What context length does Soar Mistral 123b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.

Where can I download Soar Mistral 123b GGUF?

The files are on Hugging Face in the mradermacher/Soar-mistral-123b-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 Soar Mistral 123b use?

Hugging Face lists the license as other. 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 Soar-mistral-123b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other large models

All large models →