MI

Mistral Medium 3.5 128B Eschaton Uncensored

MistralGGUF by mradermacherUpdated 2026-10-09
Download on Hugging Face
Parameters125B
Context256K
Layers88
Architecturemistral3
Smallest quant46.6 GB
Quick answer

Mistral Medium 3.5 128B Eschaton Uncensored 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 9 quants, from 46.6 GB (Q2_K) to 88.3 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

Mistral Medium 3.5 128B Eschaton Uncensored – large context, text‑only fine‑tune

Mistral Medium 3.5 128B Eschaton Uncensored is a 125‑billion‑parameter dense model with a 262,144‑token context window. It is fine‑tuned for direct, neutral responses to sensitive and technical prompts. The vision tower remains unchanged from the base model.

Good at

  • Large context reasoning
  • Direct instruction following
  • Technical content generation

Limits

  • No vision fine‑tune
  • No standard benchmarks
  • License requires review

Best for

  • Long‑form technical explanations
  • Complex reasoning tasks
  • Sensitive content handling

Who it’s for. Developers needing a large‑context LLM for detailed reasoning and instruction following. The model is suitable for applications that can tolerate the absence of vision fine‑tuning and require a neutral tone.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K46.6 GB 50.0 GB
Too big Get file →
Q3_K_S54.4 GB 57.8 GB
Too big Get file →
Q3_K_M60.6 GB 64.1 GB
Too big Get file →
Q3_K_L66.1 GB 69.5 GB
Too big Get file →
IQ4_XS67.7 GB 71.1 GB
Too big Get file →
Q4_K_S71.2 GB 74.7 GB
Too big Get file →
Q4_K_M74.9 GB 78.3 GB
Too big Get file →
Q5_K_S86.2 GB 89.6 GB
Too big Get file →
Q5_K_M88.3 GB 91.8 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (46.59 GB file, ~50 GB memory). For 12 GB VRAM, Q3_K_S (54.37 GB file, ~57.8 GB memory). For 16 GB VRAM, Q4_K_S (71.25 GB file, ~74.7 GB memory). Estimates are approximate.

What GPU do you need for Mistral Medium 3.5 128B Eschaton Uncensored?

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 Mistral Medium 3.5 128B Eschaton Uncensored quant should you choose?

Q4_K_M is the usual starting point for Mistral Medium 3.5 128B Eschaton Uncensored: it balances file size and quality well. Here it is a 74.9 GB file.

If memory is tight, the smallest file is Q2_K at 46.6 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

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

Frequently asked questions about Mistral Medium 3.5 128B Eschaton Uncensored

How much VRAM does Mistral Medium 3.5 128B Eschaton Uncensored 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 Mistral Medium 3.5 128B Eschaton Uncensored on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 50.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Medium 3.5 128B Eschaton Uncensored GGUF?

It depends on the quant: Q2_K is 46.6 GB, Q3_K_S is 54.4 GB, Q3_K_M is 60.6 GB, Q3_K_L is 66.1 GB, IQ4_XS is 67.7 GB, Q4_K_S is 71.2 GB and 3 more.

What context length does Mistral Medium 3.5 128B Eschaton Uncensored 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 Mistral Medium 3.5 128B Eschaton Uncensored GGUF?

The files are on Hugging Face in the mradermacher/Mistral-Medium-3.5-128B-Eschaton-Uncensored-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 Mistral Medium 3.5 128B Eschaton Uncensored 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 this model on 8 GB VRAM?

Yes, using the Q2_K quantization which requires about 50 GB memory at 8 k context.

Does this model support vision tasks?

The vision components are unchanged from the base model and were not fine‑tuned; no vision‑specific training was applied.

What license applies to this model?

It follows the base model’s Modified MIT License; review the license before use or redistribution.

Other GGUFs of Mistral-Medium-3.5-128B-Eschaton-Uncensored

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other large models

All large models →