GR

Granite 4.2 8b

GraniteGGUF by bartowskiUpdated 2026-08-25
Download on Hugging Face
Parameters8.79B
Context128K
Layers40
Architecturegranite
Smallest quant0.0 GB
Quick answer

Granite 4.2 8b needs about 7.4 GB of memory at Q4_K_M (a 5.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 17.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Granite 4.2 8B – a reasoning‑focused 8B LLM with 512K context

Granite 4.2 8B is an 8‑billion parameter model from IBM’s Granite family. It offers native chain‑of‑thought reasoning and flexible thinking modes. The model supports a 512K token context window and is released under Apache 2.0.

Good at

  • Built‑in chain‑of‑thought reasoning
  • Flexible thinking modes
  • Tool‑calling with reasoning

Limits

  • Large context window requires high VRAM
  • No vision support
  • Apache 2.0 license only allows text use

Best for

  • Complex math and coding tasks
  • Multi‑step logic and agentic workflows
  • Enterprise reasoning applications

Who it’s for. Developers and researchers needing a mid‑size reasoning model for text‑only workloads. The model is suitable for applications that benefit from built‑in chain‑of‑thought and flexible thinking modes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.8 GB
Fits Get file →
IQ2_M3.5 GB 5.4 GB
Fits Get file →
Q2_K3.6 GB 5.4 GB
Fits Get file →
IQ3_XXS3.7 GB 5.6 GB
Fits Get file →
IQ3_XS3.9 GB 5.8 GB
Fits Get file →
Q2_K_L4.0 GB 5.8 GB
Fits Get file →
Q3_K_S4.1 GB 5.9 GB
Fits Get file →
IQ3_M4.2 GB 6.1 GB
Fits Get file →
Q3_K_M4.5 GB 6.3 GB
Fits Get file →
Q3_K_L4.7 GB 6.6 GB
Fits Get file →
IQ4_XS4.9 GB 6.8 GB
Fits Get file →
Q3_K_XL5.1 GB 6.9 GB
Fits Get file →
Q4_05.2 GB 7.0 GB
Fits Get file →
IQ4_NL5.2 GB 7.0 GB
Fits Get file →
Q4_K_S5.2 GB 7.0 GB
Fits Get file →
Q4_K_M5.5 GB 7.4 GB
Tight Get file →
Q4_15.6 GB 7.5 GB
Tight Get file →
Q4_K_L5.8 GB 7.7 GB
Tight Get file →
Q5_K_S6.1 GB 8.0 GB
Tight Get file →
Q5_K_M6.4 GB 8.3 GB
Too big Get file →
Q5_K_L6.7 GB 8.5 GB
Too big Get file →
Q6_K7.5 GB 9.4 GB
Too big Get file →
Q6_K_L7.7 GB 9.6 GB
Too big Get file →
Q8_09.3 GB 11.2 GB
Too big Get file →
BF1617.6 GB 19.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.54 GB) or Q4_K_S (5.19 GB). For 12 GB VRAM, Q5_K_M (6.41 GB) or Q5_K_L (6.66 GB) provide better quality. Higher quants like Q6_K (7.52 GB) need 16 GB VRAM or more.

What GPU do you need for Granite 4.2 8b?

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 1.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_S (4.1 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_S (6.1 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.3 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.3 GB file, about 11.2 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (17.6 GB file, about 19.4 GB in use).

Which Granite 4.2 8b quant should you choose?

Q4_K_M is the usual starting point for Granite 4.2 8b: it balances file size and quality well. Here it is a 5.5 GB file.

The Q8_0 file is 9.3 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
Parameters8.79B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bybartowski
FamilyGranite
Licenseapache-2.0
Downloads (HF)4,908
Last updated2026-08-25

Frequently asked questions about Granite 4.2 8b

How much VRAM does Granite 4.2 8b need?

About 7.4 GB at Q4_K_M with an 8K context window. That is the 5.5 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 8b on an 8 GB GPU?

Yes, with Q5_K_S: the 6.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 4.2 8b GGUF?

It depends on the quant: file is 0.0 GB, IQ2_M is 3.5 GB, Q2_K is 3.6 GB, IQ3_XXS is 3.7 GB, IQ3_XS is 3.9 GB, Q2_K_L is 4.0 GB and 19 more.

What context length does Granite 4.2 8b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Granite 4.2 8b GGUF?

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

Yes, using Q4_K_M or Q4_K_S quantizations, which require about 7 GB VRAM at 8K context.

Does this model support vision?

No, the model only supports text input and output.

What license applies to Granite 4.2 8B?

It is released under the Apache 2.0 license, allowing commercial and academic use.

Other GGUFs of granite-4.2-8b

Similar models

Browse all →

More from bartowski

All by bartowski →

More Granite models

All Granite →

Other small models

All small models →