GR

IBM Granite 4.1 8b Heretic

GraniteGGUF by mradermacherUpdated 2026-05-05
Download on Hugging Face
Parameters8.38B
Context128K
Layers40
Architecturegranite
Smallest quant0.0 GB
Quick answer

IBM Granite 4.1 8b Heretic needs about 7.0 GB of memory at Q4_K_M (a 5.1 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 6.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

IBM Granite 4.1 8b Heretic – 8.38B parameter long‑context instruction model

IBM Granite 4.1 8b Heretic is an 8.38B parameter instruction model with a 131072 token context window. It is fine‑tuned from Granite‑4.1‑Base and supports multilingual instruction following. The model is released under Apache‑2.0.

Good at

  • Instruction following
  • Tool calling
  • Multilingual dialogue

Limits

  • Large context requires significant VRAM
  • No vision support
  • License is Apache‑2.0

Best for

  • Building AI assistants
  • Tool‑enabled agents
  • RAG applications

Who it’s for. Developers and researchers building instruction‑driven LLM applications who need a large‑context model with robust tool‑calling and multilingual support. The model is suitable for enterprise use where an Apache‑2.0 license is acceptable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.8 GB
Fits Get file →
IQ1_S2.0 GB 3.8 GB
Fits Get file →
IQ1_M2.1 GB 4.0 GB
Fits Get file →
IQ2_XXS2.4 GB 4.3 GB
Fits Get file →
IQ2_XS2.6 GB 4.5 GB
Fits Get file →
IQ2_S2.8 GB 4.6 GB
Fits Get file →
IQ2_M3.0 GB 4.8 GB
Fits Get file →
Q2_K_S3.1 GB 4.9 GB
Fits Get file →
Q2_K3.3 GB 5.1 GB
Fits Get file →
IQ3_XXS3.3 GB 5.2 GB
Fits Get file →
IQ3_XS3.6 GB 5.4 GB
Fits Get file →
Q3_K_S3.8 GB 5.6 GB
Fits Get file →
IQ3_S3.8 GB 5.6 GB
Fits Get file →
IQ3_M3.9 GB 5.8 GB
Fits Get file →
Q3_K_M4.2 GB 6.0 GB
Fits Get file →
Q3_K_L4.5 GB 6.4 GB
Fits Get file →
IQ4_XS4.6 GB 6.4 GB
Fits Get file →
Q4_04.8 GB 6.7 GB
Fits Get file →
IQ4_NL4.8 GB 6.7 GB
Fits Get file →
Q4_K_S4.9 GB 6.7 GB
Fits Get file →
Q4_K_M5.1 GB 7.0 GB
Fits Get file →
Q4_15.3 GB 7.2 GB
Fits Get file →
Q5_K_S5.8 GB 7.7 GB
Tight Get file →
Q5_K_M6.0 GB 7.8 GB
Tight Get file →
Q6_K6.9 GB 8.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.12 GB file, ~7 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (5.97 GB file, ~7.8 GB memory). For 16 GB VRAM, Q6_K (6.88 GB file, ~8.7 GB memory). Estimates are approximate.

What GPU do you need for IBM Granite 4.1 8b Heretic?

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 IQ1_M (2.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.2 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.0 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.9 GB file, about 8.7 GB in use).

Which IBM Granite 4.1 8b Heretic quant should you choose?

Q4_K_M is the usual starting point for IBM Granite 4.1 8b Heretic: it balances file size and quality well. Here it is a 5.1 GB file.

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
Parameters8.38B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)1,074
Last updated2026-05-05

Frequently asked questions about IBM Granite 4.1 8b Heretic

How much VRAM does IBM Granite 4.1 8b Heretic need?

About 7.0 GB at Q4_K_M with an 8K context window. That is the 5.1 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 IBM Granite 4.1 8b Heretic on an 8 GB GPU?

Yes, with Q5_K_M: the 6.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of IBM Granite 4.1 8b Heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.0 GB, IQ1_M is 2.1 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB and 19 more.

What context length does IBM Granite 4.1 8b Heretic 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 IBM Granite 4.1 8b Heretic GGUF?

The files are on Hugging Face in the mradermacher/IBM-granite-4.1-8b-heretic-i1-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 IBM Granite 4.1 8b Heretic 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 IBM Granite 4.1 8b Heretic on 8 GB VRAM?

Use the Q4_K_M quant, which requires about 7 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of IBM-granite-4.1-8b-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other small models

All small models →