MT

Mtreelva Dune 12B

MtreelvaGGUF by mradermacherUpdated 2026-10-21
Download on Hugging Face
Parameters12.9B
Context256K
Layers48
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Mtreelva Dune 12B needs about 21.3 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.0 GB to 10.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

Mtreelva Dune 12B – a 12.9B Gemma 4 model with reasoning and roleplay abilities

Mtreelva Dune 12B is a 12.9B parameter Gemma 4 model that merges the conversational strengths of Reelva-12B with the multilingual reasoning and coding focus of Mtrini-Tellus-12B. It is partially uncensored with reduced safety guardrails. The model supports a 262144 token context window.

Good at

  • Reasoning
  • Roleplay
  • Multilingual interaction

Limits

  • Large VRAM requirement for higher quants
  • No vision support in provided GGUFs
  • Partial uncensoring may lead to refusals

Best for

  • Chatbot development
  • Coding assistance
  • Multilingual Q&A

Who it’s for. Developers and researchers who need a large Gemma 4 model with strong reasoning and conversational capabilities. The model is suitable for local deployment using llama.cpp with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 13.4 GB
Too big Get file →
IQ1_S3.3 GB 16.7 GB
Too big Get file →
IQ1_M3.5 GB 16.9 GB
Too big Get file →
IQ2_XXS3.9 GB 17.3 GB
Too big Get file →
IQ2_XS4.2 GB 17.6 GB
Too big Get file →
IQ2_S4.5 GB 17.9 GB
Too big Get file →
IQ2_M4.8 GB 18.2 GB
Too big Get file →
Q2_K_S4.8 GB 18.2 GB
Too big Get file →
Q2_K5.2 GB 18.5 GB
Too big Get file →
IQ3_XXS5.3 GB 18.7 GB
Too big Get file →
IQ3_XS5.7 GB 19.1 GB
Too big Get file →
IQ3_S6.0 GB 19.3 GB
Too big Get file →
Q3_K_S6.0 GB 19.3 GB
Too big Get file →
IQ3_M6.2 GB 19.6 GB
Too big Get file →
Q3_K_M6.5 GB 19.9 GB
Too big Get file →
Q3_K_L7.0 GB 20.4 GB
Too big Get file →
IQ4_XS7.2 GB 20.6 GB
Too big Get file →
IQ4_NL7.5 GB 20.9 GB
Too big Get file →
Q4_07.6 GB 20.9 GB
Too big Get file →
Q4_K_S7.6 GB 21.0 GB
Too big Get file →
Q4_K_M7.9 GB 21.3 GB
Too big Get file →
Q4_18.3 GB 21.7 GB
Too big Get file →
Q5_K_S9.0 GB 22.4 GB
Too big Get file →
Q5_K_M9.2 GB 22.6 GB
Too big Get file →
Q6_K10.6 GB 24.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 3.31 GB, estimated 16.7 GB memory). For 12 GB VRAM, IQ2_S (4.22 GB, 17.6 GB memory) or Q2_K (5.16 GB, 18.5 GB memory). For 16 GB VRAM, Q3_K_M (6.52 GB, 19.9 GB memory) or Q4_K_M (7.95 GB, 21.3 GB memory).

What GPU do you need for Mtreelva Dune 12B?

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: the best quant that fits is the main file (0.0 GB file, about 13.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (10.6 GB file, about 24.0 GB in use).

Which Mtreelva Dune 12B quant should you choose?

Q4_K_M is the usual starting point for Mtreelva Dune 12B: it balances file size and quality well. Here it is a 7.9 GB file.

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

Architecturegemma4
Parameters12.9B
Layers48
Trained context262,144 tokens
KV cache (fp16)1536 KB per token

Source

Quantized bymradermacher
FamilyMtreelva
Licenseapache-2.0
Downloads (HF)4,184
Last updated2026-10-21

Frequently asked questions about Mtreelva Dune 12B

How much VRAM does Mtreelva Dune 12B need?

About 21.3 GB at Q4_K_M with an 8K context window. That is the 7.9 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 Mtreelva Dune 12B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mtreelva Dune 12B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.5 GB, IQ2_XXS is 3.9 GB, IQ2_XS is 4.2 GB, IQ2_S is 4.5 GB and 19 more.

What context length does Mtreelva Dune 12B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.

Where can I download Mtreelva Dune 12B GGUF?

The files are on Hugging Face in the mradermacher/Mtreelva-Dune-12B-i1-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 Mtreelva Dune 12B 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.

Can I run Mtreelva Dune 12B on 8 GB VRAM?

Use the IQ1_S quant, which requires about 16.7 GB memory at 8 k context. 8 GB VRAM is insufficient for full inference.

Does this model support vision inputs?

The provided GGUF files do not include vision support; the model is text‑only.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Mtreelva-Dune-12B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mtreelva models

All Mtreelva →

Other medium models

All medium models →