MI

MiLMMT 46 12B v1.0

MilmmtGGUF by mradermacherUpdated 2026-10-07
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant4.8 GB
Quick answer

MiLMMT 46 12B v1.0 needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 12.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

MiLMMT 46 12B v1.0 – a 12B Gemma3 translation model for 46 languages

MiLMMT 46 12B v1.0 is a 12‑billion‑parameter Gemma3‑based LLM trained for translation across 46 languages. It supports vision and was developed by Xiaomi Inc. The model is available in multiple GGUF quantizations.

Good at

  • Translation in 46 supported languages
  • Vision‑enabled text processing
  • Large context up to 131 072 tokens

Limits

  • No support for languages outside the 46 list
  • Requires 8 k context for memory estimates
  • No vision‑only capabilities beyond text
  • License is gemma

Best for

  • Multilingual translation tasks
  • Vision‑augmented language understanding
  • Research on multilingual LLMs

Who it’s for. Engineers and researchers needing a multilingual translation model with vision support. Suitable for developers building translation pipelines or AI applications that require both language and image inputs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 8.5 GB
Too big Get file →
Q3_K_S5.5 GB 9.2 GB
Too big Get file →
Q3_K_M6.0 GB 9.7 GB
Too big Get file →
Q3_K_L6.5 GB 10.2 GB
Too big Get file →
IQ4_XS6.6 GB 10.3 GB
Too big Get file →
Q4_K_S6.9 GB 10.7 GB
Too big Get file →
Q4_K_M7.3 GB 11.0 GB
Too big Get file →
Q5_K_S8.2 GB 12.0 GB
Too big Get file →
Q5_K_M8.4 GB 12.2 GB
Too big Get file →
Q6_K9.7 GB 13.4 GB
Too big Get file →
Q8_012.5 GB 16.2 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (4.77 GB) or Q3_K_S (5.46 GB). For 12 GB VRAM, Q4_K_M (7.30 GB) or Q5_K_S (8.23 GB) are good choices. Larger VRAM allows Q6_K (9.66 GB) or Q8_0 (12.51 GB) for higher precision.

What GPU do you need for MiLMMT 46 12B v1.0?

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: the best quant that fits is Q5_K_S (8.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).

Which MiLMMT 46 12B v1.0 quant should you choose?

Q4_K_M is the usual starting point for MiLMMT 46 12B v1.0: it balances file size and quality well. Here it is a 7.3 GB file.

The Q8_0 file is 12.5 GB, about 1.7 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 Q2_K at 4.8 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

Architecturegemma3
Parameters11.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
FamilyMilmmt
Licensegemma
Downloads (HF)6,777
Last updated2026-10-07

Frequently asked questions about MiLMMT 46 12B v1.0

How much VRAM does MiLMMT 46 12B v1.0 need?

About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 MiLMMT 46 12B v1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MiLMMT 46 12B v1.0 GGUF?

It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.0 GB, Q3_K_L is 6.5 GB, IQ4_XS is 6.6 GB, Q4_K_S is 6.9 GB and 5 more.

What context length does MiLMMT 46 12B v1.0 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download MiLMMT 46 12B v1.0 GGUF?

The files are on Hugging Face in the mradermacher/MiLMMT-46-12B-v1.0-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 MiLMMT 46 12B v1.0 use?

Hugging Face lists the license as gemma. 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 MiLMMT 46 12B v1.0 on 8 GB VRAM?

Yes, the Q2_K and Q3_K_S quantizations fit within 8 GB VRAM with estimated memory usage around 8.5–9.2 GB at 8 k context.

Does the model support languages beyond the 46 listed?

No, the model is trained only for the 46 languages specified; performance on other languages is not guaranteed.

What is the maximum context length I can use?

The model was trained on 131 072 tokens, but practical context length depends on VRAM and chosen quant.

Other GGUFs of MiLMMT-46-12B-v1.0

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Milmmt models

All Milmmt →

Other medium models

All medium models →