MI

MiLMMT 46 1B v1.0

MilmmtGGUF by mradermacherUpdated 2026-08-06
Download on Hugging Face
Parameters1B
Context32K
Layers26
Architecturegemma3
Smallest quant0.7 GB
Quick answer

MiLMMT 46 1B v1.0 needs about 1.5 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.7 GB (Q3_K_S) to 2.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

MiLMMT 46 1B v1.0 – a 1B‑parameter Gemma3 translation model

MiLMMT 46 1B v1.0 is a 1‑billion‑parameter LLM built on Gemma3. It supports 46 languages and is trained through continual pretraining, supervised fine‑tuning, reinforcement learning and model merging.

Good at

  • Multilingual translation
  • Large context handling
  • Low‑memory inference

Limits

  • No vision support
  • License is gemma
  • Only 46 languages supported

Best for

  • Chatbot translation
  • Document translation
  • Language‑specific QA

Who it’s for. Developers needing a lightweight multilingual translation model. Researchers working on low‑resource language support may also benefit.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S0.7 GB 1.4 GB
Fits Get file →
Q2_K0.7 GB 1.4 GB
Fits Get file →
IQ4_XS0.7 GB 1.4 GB
Fits Get file →
Q3_K_M0.7 GB 1.4 GB
Fits Get file →
Q3_K_L0.8 GB 1.5 GB
Fits Get file →
Q4_K_S0.8 GB 1.5 GB
Fits Get file →
Q4_K_M0.8 GB 1.5 GB
Fits Get file →
Q5_K_S0.8 GB 1.6 GB
Fits Get file →
Q5_K_M0.9 GB 1.6 GB
Fits Get file →
Q6_K1.0 GB 1.7 GB
Fits Get file →
Q8_01.1 GB 1.8 GB
Fits Get file →
F162.0 GB 2.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_S (0.78 GB) or Q4_K_M (0.81 GB). For 12 GB VRAM, Q5_K_S (0.84 GB) or Q5_K_M (0.85 GB) are suitable. Higher precision quants such as F16 (2.01 GB) require more memory but offer better accuracy.

What GPU do you need for MiLMMT 46 1B 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: the best quant that fits is F16 (2.0 GB file, about 2.7 GB in use).

Which MiLMMT 46 1B v1.0 quant should you choose?

Q4_K_M is the usual starting point for MiLMMT 46 1B v1.0: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.1 GB, about 1.3 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 Q3_K_S at 0.7 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

Architecturegemma3
Parameters1B
Layers26
Trained context32,768 tokens
KV cache (fp16)26 KB per token

Source

Quantized bymradermacher
FamilyMilmmt
Licensegemma
Downloads (HF)837
Last updated2026-08-06

Frequently asked questions about MiLMMT 46 1B v1.0

How much VRAM does MiLMMT 46 1B v1.0 need?

About 1.5 GB at Q4_K_M with an 8K context window. That is the 0.8 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 1B v1.0 on an 8 GB GPU?

Yes, with F16: the 2.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiLMMT 46 1B v1.0 GGUF?

It depends on the quant: Q3_K_S is 0.7 GB, Q2_K is 0.7 GB, IQ4_XS is 0.7 GB, Q3_K_M is 0.7 GB, Q3_K_L is 0.8 GB, Q4_K_S is 0.8 GB and 6 more.

What context length does MiLMMT 46 1B v1.0 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download MiLMMT 46 1B v1.0 GGUF?

The files are on Hugging Face in the mradermacher/MiLMMT-46-1B-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 1B 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 1B v1.0 on 8 GB VRAM?

Yes, use Q4_K_S or Q4_K_M which fit within 8 GB VRAM with approximate 1.5 GB memory usage.

Does the model support image inputs?

No, MiLMMT 46 1B v1.0 does not support vision inputs.

Which languages are supported?

The model supports 46 languages including Arabic, Chinese, English, French, German, Hindi, Japanese, Korean, Spanish, and Turkish.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Milmmt models

All Milmmt →

Other tiny models

All tiny models →