GR

Granite 4.0 H 350m Unsloth

GraniteGGUF by magiccodingmanUpdated 2026-04-25
Download on Hugging Face
Parameters340M
Context1024K
Layers32
Architecturegranitehybrid
Smallest quant0.4 GB
Quick answer

Granite 4.0 H 350m Unsloth needs about 1.7 GB of memory at MXFP4_MOE (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (MXFP4_MOE) to 0.6 GB (MXFP4_MOE). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Granite 4.0 H 350m Unsloth is a 340M-parameter Granite model in GGUF format, quantized by magiccodingman. Its trained context length is 1024K tokens. The repository has 2 quant files, from 0.4 GB (MXFP4_MOE) to 0.6 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE0.4 GB 1.7 GB
Fits Get file →
MXFP4_MOE0.6 GB 1.9 GB
Fits Get file →

What GPU do you need for Granite 4.0 H 350m Unsloth?

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 MXFP4_MOE (0.6 GB file, about 1.9 GB in use).

Which Granite 4.0 H 350m Unsloth quant should you choose?

MXFP4_MOE (0.4 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranitehybrid
Parameters340M
Layers32
Trained context1,048,576 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymagiccodingman
FamilyGranite
Licenseapache-2.0
Downloads (HF)89
Last updated2026-04-25

Frequently asked questions about Granite 4.0 H 350m Unsloth

How much VRAM does Granite 4.0 H 350m Unsloth need?

About 1.7 GB at MXFP4_MOE with an 8K context window. That is the 0.4 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 4.0 H 350m Unsloth on an 8 GB GPU?

Yes, with MXFP4_MOE: the 0.6 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 4.0 H 350m Unsloth GGUF?

It depends on the quant: MXFP4_MOE is 0.4 GB, MXFP4_MOE is 0.6 GB.

What context length does Granite 4.0 H 350m Unsloth 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 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Granite 4.0 H 350m Unsloth GGUF?

The files are on Hugging Face in the magiccodingman/Granite-4.0-H-350M-Unsloth-MagicQuant-Hybrid-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 4.0 H 350m Unsloth 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 granite-4.0-350m

Similar models

Browse all →

More from magiccodingman

All by magiccodingman →

More Granite models

All Granite →

Other tiny models

All tiny models →