MI

tosilos 128b

MistralGGUF by nesilabsUpdated 2026-08-14
Download on Hugging Face
Parameters125B
Context256K
Layers88
Architecturemistral3
Smallest quant60.6 GB
Quick answer

tosilos 128b needs about 78.3 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 2 quants, from 60.6 GB (Q3_K_M) to 74.9 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

Tosilos 128b – a 128‑billion‑parameter Mistral model fine‑tuned for cybersecurity

Tosilos 128b is a 128‑billion‑parameter Mistral3 model fine‑tuned for offensive and defensive security tasks. It inherits a 256k context window and multimodal input from its parent, Mistral‑Medium‑3.5‑128B. The model is available in two GGUF quantisations, Q3_K_M and Q4_K_M.

Good at

  • Security‑related reasoning
  • Vulnerability analysis
  • Exploit development

Limits

  • No vision output
  • License is other, not open source
  • Requires large VRAM for full precision

Best for

  • Pentesting assistants
  • Security documentation summarisation
  • Threat modelling

Who it’s for. Security professionals and researchers needing a specialised LLM for penetration testing, vulnerability assessment, and defensive strategy. The model is tailored for European cybersecurity contexts and is fine‑tuned on technical documents and exploit data.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M60.6 GB 64.1 GB
Too big Get file →
Q4_K_M74.9 GB 78.3 GB
Too big Get file →

For 8 GB VRAM use Q3_K_M (file size 60.62 GB, estimated 64.1 GB memory at 8 k context). For 12 GB VRAM use Q4_K_M (file size 74.9 GB, estimated 78.3 GB memory at 8 k context). Memory estimates are approximate.

What GPU do you need for tosilos 128b?

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 tosilos 128b quant should you choose?

Q4_K_M is the usual starting point for tosilos 128b: it balances file size and quality well. Here it is a 74.9 GB file.

If memory is tight, the smallest file is Q3_K_M at 60.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemistral3
Parameters125B
Layers88
Trained context262,144 tokens
KV cache (fp16)352 KB per token

Source

Quantized bynesilabs
FamilyMistral
Licenseother
Downloads (HF)1,325
Last updated2026-08-14

Frequently asked questions about tosilos 128b

How much VRAM does tosilos 128b need?

About 78.3 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 tosilos 128b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 64.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of tosilos 128b GGUF?

It depends on the quant: Q3_K_M is 60.6 GB, Q4_K_M is 74.9 GB.

What context length does tosilos 128b 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 tosilos 128b GGUF?

The files are on Hugging Face in the nesilabs/tosilos-128b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does tosilos 128b 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 Tosilos 128b on 8 GB VRAM?

Only with Q3_K_M quantisation; it requires about 64.1 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does this model support image output?

No, it accepts image input but outputs text only.

What license applies to Tosilos 128b?

The model is released under an other license, not open source.

Other GGUFs of Mistral-Medium-3.5-128B

Similar models

Browse all →

More from nesilabs

All by nesilabs →

More Mistral models

All Mistral →

Other large models

All large models →