GR

Granite-4.1-8B

GraniteGGUF by unslothUpdated 2026-04-30
Download on Hugging Face
Parameters8.79B
Context128K
Layers40
Architecturegranite
Smallest quant3.3 GB
Quick answer

Granite-4.1-8B needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 3.3 GB (IQ2_M) to 17.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Granite‑4.1‑8B – 8B‑parameter long‑context instruction model

Granite‑4.1‑8B is an 8B‑parameter model with a 131 072‑token context window. It is fine‑tuned from Granite‑4.1‑Base with supervised and RL alignment for instruction following, tool calling, and chat. The model supports multiple languages and is licensed under Apache 2.0.

Good at

  • Instruction following
  • Tool calling
  • Multilingual dialogue

Limits

  • Large context requires high VRAM
  • No vision support
  • Apache 2.0 license

Best for

  • Building AI assistants
  • LLM agents with tool use
  • Business chatbots

Who it’s for. Developers and researchers building instruction‑driven applications who need a large‑context model with strong tool‑calling and multilingual capabilities. The model is suitable for on‑premise deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M3.3 GB 5.1 GB
Fits Get file →
IQ3_XXS3.6 GB 5.4 GB
Fits Get file →
Q2_K_XL3.6 GB 5.5 GB
Fits Get file →
Q3_K_S3.9 GB 5.8 GB
Fits Get file →
Q3_K_M4.3 GB 6.2 GB
Fits Get file →
Q3_K_XL4.6 GB 6.4 GB
Fits Get file →
IQ4_XS4.8 GB 6.7 GB
Fits Get file →
Q4_05.1 GB 6.9 GB
Fits Get file →
IQ4_NL5.1 GB 6.9 GB
Fits Get file →
Q4_K_S5.1 GB 6.9 GB
Fits Get file →
Q4_K_M5.3 GB 7.2 GB
Fits Get file →
Q4_K_XL5.5 GB 7.3 GB
Tight Get file →
Q4_15.6 GB 7.4 GB
Tight Get file →
Q5_K_S6.1 GB 7.9 GB
Tight Get file →
Q5_K_M6.3 GB 8.1 GB
Too big Get file →
Q5_K_XL6.3 GB 8.1 GB
Too big Get file →
Q6_K7.2 GB 9.1 GB
Too big Get file →
Q6_K_XL7.9 GB 9.8 GB
Too big Get file →
Q8_09.3 GB 11.2 GB
Too big Get file →
Q8_K_XL11.2 GB 13.1 GB
Too big Get file →
BF1617.6 GB 19.4 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (≈7.2 GB memory at 8 k context). With 12 GB VRAM Q5_K_M (≈8.1 GB) or Q6_K (≈9.1 GB) are viable. For 16 GB VRAM Q6_K_XL (≈9.8 GB) or Q8_0 (≈11.2 GB) provide higher quality.

What GPU do you need for Granite-4.1-8B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_S (3.9 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_S (6.1 GB file, about 7.9 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_K_XL (11.2 GB file, about 13.1 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-4.1-8B quant should you choose?

Q4_K_M is the usual starting point for Granite-4.1-8B: it balances file size and quality well. Here it is a 5.3 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 IQ2_M at 3.3 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
Parameters8.79B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byunsloth
FamilyGranite
Licenseapache-2.0
Downloads (HF)5,259
Last updated2026-04-30

Frequently asked questions about Granite-4.1-8B

How much VRAM does Granite-4.1-8B need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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-4.1-8B on an 8 GB GPU?

Yes, with Q5_K_S: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite-4.1-8B GGUF?

It depends on the quant: IQ2_M is 3.3 GB, IQ3_XXS is 3.6 GB, Q2_K_XL is 3.6 GB, Q3_K_S is 3.9 GB, Q3_K_M is 4.3 GB, Q3_K_XL is 4.6 GB and 15 more.

What context length does Granite-4.1-8B 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-4.1-8B GGUF?

The files are on Hugging Face in the unsloth/granite-4.1-8b-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-4.1-8B 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‑4.1‑8B on 8 GB VRAM?

Use the Q4_K_M quant, which requires about 7.2 GB of VRAM at 8 k context. The file size is 5.35 GB.

Does the model support image inputs?

No, Granite‑4.1‑8B does not have vision capabilities.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of granite-4.1-8b

Similar models

Browse all →

More from unsloth

All by unsloth →

More Granite models

All Granite →

Other small models

All small models →