Skip to content

Text model · Mistral

Devstral 2 123B: RAM and VRAM requirements

Devstral 2 123B needs about 73.3 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~69.75 GB to download; KV cache and overhead add the rest), or about 127.2 GB at Q8_0. The lightest hardware that runs it is Apple M4 Max (128GB).

Mistral family · 123B params · released Dec 2025 · 353.3K Ollama pulls.

Shopping for hardware? See what runs Devstral 2 123B →

License Modified MIT · Conditional ↓ 19K/mo ♥ 338 on HuggingFace
Q4_K_M GGUF
69.75 GB
Q8_0 GGUF
123.73 GB
Memory @ Q4 (4k)
~73.3 GB
Context
256 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

Devstral 2 123B runs on 4 of 43 tracked devices at Q4_K_M.

4 run well 0 tight fit 39 too small
Fit check Q4_K_M
No, not enough memory
needs 73.3 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)69.75 GB
+
KV cache (4k)2.7 GB
+
Overhead0.8 GB
=
Total73.3 GB

How context length changes it

4k context ~73.3 GB 32k context ~91.9 GB 128k context ~155.8 GB

Longer context grows the KV cache quickly: Devstral 2 123B needs ~73.3 GB at 4k but ~155.8 GB at 128k, which can push it past a device that fits it at a short context.

Speed drops too: every token re-reads the KV cache, so at 128k context Devstral 2 123B generates at roughly ~45% of its short-context speed. How this is estimated.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 51.5 GB est
Q3_K_M 60.1 GB est
Q4_K_M (default) 69.75 GB
Q5_K_M 87.6 GB est
Q6_K 100.9 GB est
Q8_0 123.73 GB
FP16 250.06 GB

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run devstral-2:123b
llama.cpp
$ llama-cli -hf unsloth/Devstral-2-123B-Instruct-2512-GGUF:Q4_K_M
LM Studio
$ lms get unsloth/Devstral-2-123B-Instruct-2512-GGUF

Which devices can run Devstral 2 123B?

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Similar models

Head-to-head

FAQ

How much VRAM or RAM does Devstral 2 123B need?

At Q4_K_M, Devstral 2 123B needs about 73.3 GB (weights ~69.75 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~127.2 GB.

What is the Q4_K_M GGUF file size of Devstral 2 123B?

The Q4_K_M GGUF file is about 69.75 GB to download, and the Q8_0 GGUF is about 123.73 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~73.3 GB of memory at Q4_K_M.

Can Devstral 2 123B run on a laptop?

Devstral 2 123B is large; you need a high-memory Mac or multi-GPU setup at Q4_K_M.

Can I use Devstral 2 123B commercially?

Conditionally. Modified MIT: free below a stated revenue threshold, extra terms above it (see the LICENSE file).

Understand the numbers

Short guides to the ideas behind Devstral 2 123B's memory and quant figures.

Mistral's large agentic coding model: dense 123B, 256K context. Q4_K_M is a 74.9GB two-file split from unsloth, so it needs a 96GB-class machine even quantized. Modified MIT license with a revenue threshold.

Sources

Last validated 2026-09-07. Memory figures are estimates. See methodology.