MI

mistralai_Leanstral 2603

MistralGGUF by jackcloudmanUpdated 2026-03-17
Download on Hugging Face
Parameters119B
Context1024K
Layers36
Architecturedeepseek2
Smallest quant72.2 GB
Quick answer

mistralai_Leanstral 2603 needs about 73.0 GB of memory at Q4_K_M (a 72.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 72.2 GB (Q4_K_M) to 126.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.

mistralai_Leanstral 2603 is a 119B-parameter Mistral model in GGUF format, quantized by jackcloudman. Its trained context length is 1024K tokens. The repository has 2 quant files, from 72.2 GB (Q4_K_M) to 126.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M72.2 GB 73.0 GB
Too big Get file →
Q8_0126.5 GB 127.3 GB
Too big Get file →

What GPU do you need for mistralai_Leanstral 2603?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which mistralai_Leanstral 2603 quant should you choose?

Q4_K_M is the usual starting point for mistralai_Leanstral 2603: it balances file size and quality well. Here it is a 72.2 GB file.

The Q8_0 file is 126.5 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters119B (approximate, mixture of experts)
Layers36
Trained context1,048,576 tokens
KV cache (fp16)41 KB per token

Source

Quantized byjackcloudman
FamilyMistral
Licenseapache-2.0
Downloads (HF)77
Last updated2026-03-17

Frequently asked questions about mistralai_Leanstral 2603

How much VRAM does mistralai_Leanstral 2603 need?

About 73.0 GB at Q4_K_M with an 8K context window. That is the 72.2 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 mistralai_Leanstral 2603 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 73.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mistralai_Leanstral 2603 GGUF?

It depends on the quant: Q4_K_M is 72.2 GB, Q8_0 is 126.5 GB.

What context length does mistralai_Leanstral 2603 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.4 GB at 32K.

Where can I download mistralai_Leanstral 2603 GGUF?

The files are on Hugging Face in the jackcloudman/Leanstral-2603-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 mistralai_Leanstral 2603 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.

Similar models

Browse all →

More from jackcloudman

All by jackcloudman →

More Mistral models

All Mistral →

Other large models

All large models →