GR

granite-4.0-micro-base

GraniteGGUF by MungertUpdated 2025-10-22
Download on Hugging Face
Parameters3.4B
Context128K
Layers40
Architecturegranite
Smallest quant0.0 GB
Quick answer

granite-4.0-micro-base needs about 6.0 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 27 quants, from 0.0 GB to 6.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 13.4 GB.

Granite‑4.0‑Micro‑Base: 3.4B decoder‑only model with 131072 token context

Granite‑4.0‑Micro‑Base is a 3.4B parameter decoder‑only language model with a 131072 token context window. It is trained from scratch on approximately 15 trillion tokens and supports Fill‑in‑the‑Middle code completion. The model is released under Apache 2.0.

Good at

  • Long‑context text generation
  • Fill‑in‑the‑Middle code completion
  • Multilingual support

Limits

  • Large VRAM requirement for higher precision quants
  • No vision support
  • No mixture of experts

Best for

  • Chatbots needing long context
  • Code completion tools
  • Research prototyping

Who it’s for. Developers and researchers who need a small‑to‑medium sized model with a very long context window and multilingual capabilities. The model is suitable for local deployment on machines with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.9 GB
Fits Get file →
IQ1_S1.0 GB 4.8 GB
Fits Get file →
IQ1_M1.1 GB 4.9 GB
Fits Get file →
IQ2_XXS1.1 GB 5.0 GB
Fits Get file →
IQ2_XS1.2 GB 5.0 GB
Fits Get file →
IQ2_S1.2 GB 5.1 GB
Fits Get file →
IQ2_M1.3 GB 5.1 GB
Fits Get file →
Q2_K_S1.3 GB 5.1 GB
Fits Get file →
Q2_K_M1.3 GB 5.2 GB
Fits Get file →
IQ3_XXS1.5 GB 5.3 GB
Fits Get file →
IQ3_XS1.5 GB 5.4 GB
Fits Get file →
IQ3_M1.7 GB 5.5 GB
Fits Get file →
Q3_K_S1.7 GB 5.5 GB
Fits Get file →
Q3_K_M1.7 GB 5.6 GB
Fits Get file →
IQ4_XS1.9 GB 5.7 GB
Fits Get file →
IQ4_NL1.9 GB 5.8 GB
Fits Get file →
Q4_K_S2.0 GB 5.9 GB
Fits Get file →
Q4_02.0 GB 5.9 GB
Fits Get file →
Q4_K_M2.1 GB 6.0 GB
Fits Get file →
Q4_12.1 GB 6.0 GB
Fits Get file →
Q5_02.4 GB 6.3 GB
Fits Get file →
Q5_K_M2.5 GB 6.4 GB
Fits Get file →
Q5_12.6 GB 6.5 GB
Fits Get file →
Q6_K_M2.9 GB 6.7 GB
Fits Get file →
Q8_03.6 GB 7.5 GB
Tight Get file →
F164.9 GB 8.8 GB
Too big Get file →
BF166.8 GB 10.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.14 GB, memory 6 GB) or Q4_1 (2.15 GB, 6 GB). If 12 GB VRAM is available, Q5_0 (2.44 GB, 6.3 GB) or Q5_K_M (2.51 GB, 6.4 GB) provide better precision. For 16 GB VRAM, Q6_K_M (2.86 GB, 6.7 GB) or Q8_0 (3.62 GB, 7.5 GB) are recommended.

What GPU do you need for granite-4.0-micro-base?

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 the main file (0.0 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_1 (2.1 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (6.8 GB file, about 10.7 GB in use).

Which granite-4.0-micro-base quant should you choose?

Q4_K_M is the usual starting point for granite-4.0-micro-base: it balances file size and quality well. Here it is a 2.1 GB file.

The Q8_0 file is 3.6 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 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

Architecturegranite
Parameters3.4B
Layers40
Trained context131,072 tokens
KV cache (fp16)400 KB per token

Source

Quantized byMungert
FamilyGranite
Licenseapache-2.0
Downloads (HF)2,280
Last updated2025-10-22

Frequently asked questions about granite-4.0-micro-base

How much VRAM does granite-4.0-micro-base need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 2.1 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 granite-4.0-micro-base on an 8 GB GPU?

Yes, with Q8_0: the 3.6 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of granite-4.0-micro-base GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.0 GB, IQ1_M is 1.1 GB, IQ2_XXS is 1.1 GB, IQ2_XS is 1.2 GB, IQ2_S is 1.2 GB and 21 more.

What context length does granite-4.0-micro-base support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.4 GB at 8K and 13.4 GB at 32K.

Where can I download granite-4.0-micro-base GGUF?

The files are on Hugging Face in the Mungert/granite-4.0-micro-base-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 granite-4.0-micro-base 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 this model on 8 GB VRAM?

Yes, with Q4_K_M or Q4_1 quantization, which use about 6 GB of VRAM at 8 k context.

Does this model support vision tasks?

No, it is a text‑only decoder‑only model.

What license applies to this model?

The model is released under the Apache 2.0 license.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Granite models

All Granite →

Other tiny models

All tiny models →