GR

Granite 4.2 3b

GraniteGGUF by bartowskiUpdated 2026-08-25
Download on Hugging Face
Parameters3.66B
Context128K
Layers40
Architecturegranite
Smallest quant0.0 GB
Quick answer

Granite 4.2 3b needs about 3.5 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 7.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Granite 4.2 3b – compact reasoning model with native chain‑of‑thought

Granite 4.2 3b is a 3.66 billion‑parameter dense transformer designed for reasoning tasks. It supports a 131072‑token context window and offers flexible thinking modes. The model is released under Apache 2.0 and can be run with llama.cpp.

Good at

  • Native chain‑of‑thought reasoning
  • Tool‑calling with reasoning
  • Long‑context support

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • Large VRAM needed for higher‑quality quants

Best for

  • Math and coding problem solving
  • Agentic tool‑calling workflows
  • Long‑document summarization

Who it’s for. Developers and researchers needing a small, reasoning‑capable LLM for local deployment. The model is fully open‑source under Apache 2.0, suitable for commercial or academic use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.2 GB
Fits Get file →
IQ2_M1.5 GB 2.7 GB
Fits Get file →
Q2_K1.5 GB 2.7 GB
Fits Get file →
IQ3_XXS1.6 GB 2.7 GB
Fits Get file →
IQ3_XS1.7 GB 2.8 GB
Fits Get file →
Q3_K_S1.7 GB 2.9 GB
Fits Get file →
Q2_K_L1.8 GB 2.9 GB
Fits Get file →
IQ3_M1.8 GB 3.0 GB
Fits Get file →
Q3_K_M1.9 GB 3.1 GB
Fits Get file →
Q3_K_L2.0 GB 3.2 GB
Fits Get file →
IQ4_XS2.1 GB 3.2 GB
Fits Get file →
Q4_02.2 GB 3.3 GB
Fits Get file →
IQ4_NL2.2 GB 3.3 GB
Fits Get file →
Q4_K_S2.2 GB 3.4 GB
Fits Get file →
Q3_K_XL2.2 GB 3.4 GB
Fits Get file →
Q4_K_M2.3 GB 3.5 GB
Fits Get file →
Q4_12.4 GB 3.5 GB
Fits Get file →
Q4_K_L2.5 GB 3.7 GB
Fits Get file →
Q5_K_S2.6 GB 3.7 GB
Fits Get file →
Q5_K_M2.7 GB 3.8 GB
Fits Get file →
Q5_K_L2.8 GB 4.0 GB
Fits Get file →
Q6_K3.1 GB 4.3 GB
Fits Get file →
Q6_K_L3.2 GB 4.4 GB
Fits Get file →
Q8_03.9 GB 5.1 GB
Fits Get file →
BF167.3 GB 8.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.32 GB) or Q4_K_L (2.51 GB). For 12 GB VRAM, Q5_K_M (2.67 GB) or Q6_K (3.12 GB) provide better quality. The Q8_0 quant (3.89 GB) offers the highest fidelity but needs 16 GB VRAM.

What GPU do you need for Granite 4.2 3b?

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 Q5_K_L (2.8 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.9 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.9 GB file, about 5.1 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.3 GB file, about 8.5 GB in use).

Which Granite 4.2 3b quant should you choose?

Q4_K_M is the usual starting point for Granite 4.2 3b: it balances file size and quality well. Here it is a 2.3 GB file.

The Q8_0 file is 3.9 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
Parameters3.66B
Layers40
Trained context131,072 tokens
KV cache (fp16)80 KB per token

Source

Quantized bybartowski
FamilyGranite
Licenseapache-2.0
Downloads (HF)3,543
Last updated2026-08-25

Frequently asked questions about Granite 4.2 3b

How much VRAM does Granite 4.2 3b need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.3 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 Granite 4.2 3b on an 8 GB GPU?

Yes, with Q8_0: the 3.9 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 4.2 3b GGUF?

It depends on the quant: file is 0.0 GB, IQ2_M is 1.5 GB, Q2_K is 1.5 GB, IQ3_XXS is 1.6 GB, IQ3_XS is 1.7 GB, Q3_K_S is 1.7 GB and 19 more.

What context length does Granite 4.2 3b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Granite 4.2 3b GGUF?

The files are on Hugging Face in the bartowski/granite-4.2-3b-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 4.2 3b 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 Granite 4.2 3b on 8 GB VRAM?

Yes, with the Q4_K_M quant (2.32 GB) or Q4_K_L (2.51 GB).

Does this model support vision?

No, it only supports text input.

What context length does it support?

It supports up to 131072 tokens.

Other GGUFs of granite-4.2-3b

Similar models

Browse all →

More from bartowski

All by bartowski →

More Granite models

All Granite →

Other small models

All small models →