MI

Devstral 2 123B Instruct 2512

MistralGGUF by bartowskiUpdated 2025-12-10
Download on Hugging Face
Parameters125B
Context256K
Layers88
Architecturellama
Smallest quant0.0 GB
Quick answer

Devstral 2 123B Instruct 2512 needs about 78.4 GB of memory at Q4_K_M (a 74.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 0.0 GB to 132.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

Devstral 2 123B Instruct 2512 – a large LLM for agentic coding tasks

Devstral 2 123B Instruct 2512 is a 125‑billion parameter model fine‑tuned in FP8 for instruction following. It offers a 262144‑token context window and is optimized for software engineering tasks such as code editing and tool integration.

Good at

  • Agentic coding
  • Tool‑based codebase exploration
  • Instruction‑driven software tasks

Limits

  • Large memory requirement for full precision
  • No vision support
  • License is other, not open source

Best for

  • AI code assistants
  • Software engineering agents
  • Complex tool‑chain workflows

Who it’s for. Developers and enterprises needing advanced coding assistance and agentic code generation. The model is suitable for teams that can allocate sufficient GPU memory and are comfortable with the non‑open‑source license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.5 GB
Fits Get file →
IQ1_S27.2 GB 30.6 GB
Too big Get file →
IQ1_M29.6 GB 33.1 GB
Too big Get file →
IQ2_XXS33.7 GB 37.1 GB
Too big Get file →
IQ2_XS37.3 GB 40.8 GB
Too big Get file →
IQ2_S39.7 GB 43.2 GB
Too big Get file →
IQ2_M43.0 GB 46.4 GB
Too big Get file →
Q2_K46.6 GB 50.0 GB
Too big Get file →
Q2_K_L48.2 GB 51.6 GB
Too big Get file →
IQ3_XXS48.4 GB 51.8 GB
Too big Get file →
IQ3_XS51.7 GB (2 parts) 55.1 GB
Too big Get file →
Q3_K_S54.4 GB (2 parts) 57.8 GB
Too big Get file →
IQ3_M56.8 GB (2 parts) 60.2 GB
Too big Get file →
Q3_K_M60.6 GB (2 parts) 64.1 GB
Too big Get file →
Q3_K_L66.1 GB (2 parts) 69.5 GB
Too big Get file →
IQ4_XS67.1 GB (2 parts) 70.5 GB
Too big Get file →
Q3_K_XL67.5 GB (2 parts) 70.9 GB
Too big Get file →
IQ4_NL70.9 GB (2 parts) 74.3 GB
Too big Get file →
Q4_071.0 GB (2 parts) 74.5 GB
Too big Get file →
Q4_K_S71.2 GB (2 parts) 74.7 GB
Too big Get file →
Q4_K_M74.9 GB (2 parts) 78.4 GB
Too big Get file →
Q4_K_L76.1 GB (2 parts) 79.5 GB
Too big Get file →
Q4_178.5 GB (2 parts) 81.9 GB
Too big Get file →
Q5_K_S86.2 GB (3 parts) 89.6 GB
Too big Get file →
Q5_K_M88.3 GB (3 parts) 91.8 GB
Too big Get file →
Q6_K102.6 GB (3 parts) 106.0 GB
Too big Get file →
Q8_0132.9 GB (4 parts) 136.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 71 GB, estimated 74.5 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (74.9 GB, 78.4 GB memory). For 16 GB VRAM, Q5_K_S (86.18 GB, 89.6 GB memory). Larger VRAM allows higher‑quality quants such as Q6_K or Q8_0.

What GPU do you need for Devstral 2 123B Instruct 2512?

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: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.5 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ1_S (27.2 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_M (43.0 GB file, about 46.4 GB in use).

Which Devstral 2 123B Instruct 2512 quant should you choose?

Q4_K_M is the usual starting point for Devstral 2 123B Instruct 2512: it balances file size and quality well. Here it is a 74.9 GB file.

The Q8_0 file is 132.9 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters125B
Layers88
Trained context262,144 tokens
KV cache (fp16)352 KB per token

Source

Quantized bybartowski
FamilyMistral
Licenseother
Downloads (HF)2,824
Last updated2025-12-10

Frequently asked questions about Devstral 2 123B Instruct 2512

How much VRAM does Devstral 2 123B Instruct 2512 need?

About 78.4 GB at Q4_K_M with an 8K context window. That is the 74.9 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 Devstral 2 123B Instruct 2512 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Devstral 2 123B Instruct 2512 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 27.2 GB, IQ1_M is 29.6 GB, IQ2_XXS is 33.7 GB, IQ2_XS is 37.3 GB, IQ2_S is 39.7 GB and 21 more.

What context length does Devstral 2 123B Instruct 2512 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Devstral 2 123B Instruct 2512 GGUF?

The files are on Hugging Face in the bartowski/mistralai_Devstral-2-123B-Instruct-2512-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 Devstral 2 123B Instruct 2512 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.

Can I run Devstral 2 123B Instruct 2512 on 8 GB VRAM?

Only with the lowest‑quality quant, Q4_0, which still requires about 74.5 GB memory at 8k context. 8 GB VRAM is insufficient.

Does the model support vision tasks?

No, the model has no vision capability.

Is the model open source?

The license is listed as other; it is not an open‑source license.

Other GGUFs of Devstral-2-123B-Instruct-2512

Similar models

Browse all →

More from bartowski

All by bartowski →

More Mistral models

All Mistral →

Other large models

All large models →