Granite 4.0 H 350m needs about 1.5 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.2 GB (Q2_K) to 0.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Granite 4.0 H 350m – lightweight instruct model for on‑device use
Granite 4.0 H 350m is a 350 M parameter instruct model finetuned from Granite‑4.0‑H‑350M‑Base. It supports multiple languages and instruction following, and is available in GGUF format with several quantizations.
Good at
- Instruction following
- Multilingual dialog
- Tool‑calling
Limits
- No vision support
- Requires 1.5–2 GB VRAM for 8 k context
- Apache‑2.0 license
Best for
- On‑device chat assistants
- Fine‑tuning for niche domains
- Code completion with function calling
Who it’s for. Developers and researchers needing a compact, multilingual LLM that can run on modest hardware. The model is suitable for local deployments and fine‑tuning on specialized data sets.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.2 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_S | 0.2 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 1.5 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 1.5 GB | Fits | Get file → | |
| Q4_1 | 0.2 GB | 1.5 GB | Fits | Get file → | |
| Q5_0 | 0.2 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_S | 0.2 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.6 GB | Fits | Get file → | |
| Q5_1 | 0.3 GB | 1.6 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 1.6 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.7 GB | Fits | Get file → | |
| BF16 | 0.7 GB | 2.0 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K or Q4_0 (0.22 GB) gives a good balance of size and performance. If memory is tighter, use Q2_K (0.16 GB). For higher precision, Q5_0 (0.25 GB) or BF16 (0.68 GB) are available, but require more VRAM.
What GPU do you need for Granite 4.0 H 350m?
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 BF16 (0.7 GB file, about 2.0 GB in use).
Which Granite 4.0 H 350m quant should you choose?
Q4_K_M is the usual starting point for Granite 4.0 H 350m: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.4 GB, about 1.6 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 0.2 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
Source
Frequently asked questions about Granite 4.0 H 350m
How much VRAM does Granite 4.0 H 350m need?
About 1.5 GB at Q4_K_M with an 8K context window. That is the 0.2 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 on an 8 GB GPU?
Yes, with BF16: the 0.7 GB file needs about 2.0 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 GGUF?
It depends on the quant: Q2_K is 0.2 GB, Q3_K_S is 0.2 GB, Q3_K_M is 0.2 GB, Q3_K_L is 0.2 GB, Q4_0 is 0.2 GB, Q4_K_S is 0.2 GB and 9 more.
What context length does Granite 4.0 H 350m 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 GGUF?
The files are on Hugging Face in the ibm-granite/granite-4.0-h-350m-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 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 4.0 H 350m on 8 GB VRAM?
Yes, quantizations such as Q4_K or Q4_0 use about 1.5 GB VRAM at 8 k context, fitting comfortably in 8 GB.
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.