GR

Half Granite Marvin

GraniteGGUF by mradermacherUpdated 2025-12-07
Download on Hugging Face
Parameters32.2B
Context1024K
Layers40
Architecturegranitehybrid
Smallest quant0.1 GB
Quick answer

Half Granite Marvin needs about 25.3 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.1 GB to 26.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 21.5 GB.

Half Granite Marvin is a 32.2B-parameter Granite model in GGUF format, quantized by mradermacher. Its trained context length is 1024K tokens. The repository has 24 quant files, from 0.1 GB to 26.5 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 6.0 GB
Fits Get file →
IQ1_S6.7 GB 12.5 GB
Too big Get file →
IQ1_M7.4 GB 13.2 GB
Too big Get file →
IQ2_XXS8.6 GB 14.5 GB
Too big Get file →
IQ2_XS9.6 GB 15.4 GB
Too big Get file →
IQ2_S9.6 GB 15.5 GB
Too big Get file →
IQ2_M10.6 GB 16.5 GB
Too big Get file →
Q2_K_S11.1 GB 17.0 GB
Too big Get file →
Q2_K11.8 GB 17.6 GB
Too big Get file →
IQ3_XXS12.5 GB 18.4 GB
Too big Get file →
IQ3_XS13.4 GB 19.3 GB
Too big Get file →
IQ3_S14.1 GB 19.9 GB
Too big Get file →
Q3_K_S14.1 GB 19.9 GB
Too big Get file →
IQ3_M14.2 GB 20.1 GB
Too big Get file →
Q3_K_M15.4 GB 21.2 GB
Too big Get file →
Q3_K_L16.5 GB 22.3 GB
Too big Get file →
IQ4_XS17.3 GB 23.1 GB
Too big Get file →
Q4_018.3 GB 24.2 GB
Too big Get file →
Q4_K_S18.4 GB 24.3 GB
Too big Get file →
Q4_K_M19.5 GB 25.3 GB
Too big Get file →
Q4_120.3 GB 26.1 GB
Too big Get file →
Q5_K_S22.2 GB 28.1 GB
Too big Get file →
Q5_K_M22.9 GB 28.7 GB
Too big Get file →
Q6_K26.5 GB 32.3 GB
Too big Get file →

What GPU do you need for Half Granite Marvin?

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 the main file (0.1 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 6.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_S (9.6 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (17.3 GB file, about 23.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (22.9 GB file, about 28.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (26.5 GB file, about 32.3 GB in use).

Which Half Granite Marvin quant should you choose?

Q4_K_M is the usual starting point for Half Granite Marvin: it balances file size and quality well. Here it is a 19.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 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

Architecturegranitehybrid
Parameters32.2B (approximate, mixture of experts)
Layers40
Trained context1,048,576 tokens
KV cache (fp16)640 KB per token

Source

Quantized bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)319
Last updated2025-12-07

Frequently asked questions about Half Granite Marvin

How much VRAM does Half Granite Marvin need?

About 25.3 GB at Q4_K_M with an 8K context window. That is the 19.5 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 Half Granite Marvin on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Half Granite Marvin GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 6.7 GB, IQ1_M is 7.4 GB, IQ2_XXS is 8.6 GB, IQ2_XS is 9.6 GB, IQ2_S is 9.6 GB and 18 more.

What context length does Half Granite Marvin support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 5.4 GB at 8K and 21.5 GB at 32K.

Where can I download Half Granite Marvin GGUF?

The files are on Hugging Face in the mradermacher/half-granite-marvin-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 Half Granite Marvin 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.

Other GGUFs of half-granite-marvin

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other medium models

All medium models →