GR

Granite 4.2 30b

GraniteGGUF by ibm-graniteUpdated 2026-09-02
Download on Hugging Face
Parameters29.3B
Context128K
Layers64
Architecturegranite
Smallest quant10.9 GB
Quick answer

Granite 4.2 30b needs about 20.4 GB of memory at Q4_K_M (a 17.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 15 quants, from 10.9 GB (Q2_K) to 58.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Granite 4.2 30B – a large reasoning model with native chain‑of‑thought

Granite 4.2 30B is a 30‑billion‑parameter decoder‑only model built on the granite architecture. It offers native chain‑of‑thought reasoning and flexible thinking modes. The model is released under Apache 2.0 and supports a 512K context window.

Good at

  • Native chain‑of‑thought reasoning
  • Flexible thinking modes
  • Long‑context handling

Limits

  • 512K context window only
  • No vision support
  • Large VRAM requirement for high‑precision quants

Best for

  • Complex math and coding tasks
  • Multi‑step logic problems
  • Agentic tool‑calling workflows

Who it’s for. Researchers and enterprises needing advanced reasoning in a commercial‑friendly license. The model is suitable for applications that require deep step‑by‑step logic and long‑document understanding.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.9 GB 13.5 GB
Too big Get file →
Q3_K_S12.7 GB 15.4 GB
Too big Get file →
Q3_K_M14.1 GB 16.8 GB
Too big Get file →
Q3_K_L15.3 GB 18.0 GB
Too big Get file →
Q4_016.6 GB 19.2 GB
Too big Get file →
Q4_K_S16.7 GB 19.4 GB
Too big Get file →
Q4_K_M17.7 GB 20.4 GB
Too big Get file →
Q4_118.4 GB 21.0 GB
Too big Get file →
Q5_020.2 GB 22.8 GB
Too big Get file →
Q5_K_S20.2 GB 22.8 GB
Too big Get file →
Q5_K_M20.8 GB 23.4 GB
Too big Get file →
Q5_122.0 GB 24.6 GB
Too big Get file →
Q6_K24.0 GB 26.7 GB
Too big Get file →
Q8_031.1 GB 33.8 GB
Too big Get file →
BF1658.6 GB (2 parts) 61.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (17.72 GB file, ~20.4 GB VRAM). For 12 GB VRAM, Q5_K_M (20.78 GB file, ~23.4 GB VRAM). Higher‑precision quants like Q8_0 or BF16 need 32 GB+ VRAM and are not recommended for low‑budget GPUs.

What GPU do you need for Granite 4.2 30b?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q3_K_S (12.7 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (20.8 GB file, about 23.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (24.0 GB file, about 26.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (31.1 GB file, about 33.8 GB in use).

Which Granite 4.2 30b quant should you choose?

Q4_K_M is the usual starting point for Granite 4.2 30b: it balances file size and quality well. Here it is a 17.7 GB file.

The Q8_0 file is 31.1 GB, about 1.8 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 10.9 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

Architecturegranite
Parameters29.3B
Layers64
Trained context131,072 tokens
KV cache (fp16)256 KB per token

Source

Quantized byibm-granite
FamilyGranite
Licenseapache-2.0
Downloads (HF)238,984
Last updated2026-09-02

Frequently asked questions about Granite 4.2 30b

How much VRAM does Granite 4.2 30b need?

About 20.4 GB at Q4_K_M with an 8K context window. That is the 17.7 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 30b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Granite 4.2 30b GGUF?

It depends on the quant: Q2_K is 10.9 GB, Q3_K_S is 12.7 GB, Q3_K_M is 14.1 GB, Q3_K_L is 15.3 GB, Q4_0 is 16.6 GB, Q4_K_S is 16.7 GB and 9 more.

What context length does Granite 4.2 30b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Granite 4.2 30b GGUF?

The files are on Hugging Face in the ibm-granite/granite-4.2-30b-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 30b 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.

Does the model support vision tasks?

No, Granite 4.2 30B is a text‑only model.

What license applies to this model?

Apache 2.0, allowing unrestricted commercial and academic use.

Other GGUFs of granite-4.2-30b

Similar models

Browse all →

More from ibm-granite

All by ibm-granite →

More Granite models

All Granite →

Other medium models

All medium models →