GR

GRaPE Nano

GrapeGGUF by SL-AIUpdated 2026-03-18
Download on Hugging Face
Parameters742M
Context125K
Layers16
Architecturelfm2
Smallest quant0.3 GB
Quick answer

GRaPE Nano needs about 1.8 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.3 GB (Q2_K) to 1.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

GRaPE Nano is a 742M-parameter Grape model in GGUF format, quantized by SL-AI. Its trained context length is 125K tokens. The repository has 4 quant files, from 0.3 GB (Q2_K) to 1.5 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.3 GB 1.6 GB
Fits Get file →
Q4_K_M0.5 GB 1.8 GB
Fits Get file →
Q6_K0.6 GB 1.9 GB
Fits Get file →
BF161.5 GB 2.8 GB
Fits Get file →

What GPU do you need for GRaPE Nano?

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 (1.5 GB file, about 2.8 GB in use).

Which GRaPE Nano quant should you choose?

Q4_K_M is the usual starting point for GRaPE Nano: it balances file size and quality well. Here it is a 0.5 GB file.

If memory is tight, the smallest file is Q2_K at 0.3 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

Architecturelfm2
Parameters742M
Layers16
Trained context128,000 tokens
KV cache (fp16)96 KB per token

Source

Quantized bySL-AI
FamilyGrape
Licenseapache-2.0
Downloads (HF)121
Last updated2026-03-18

Frequently asked questions about GRaPE Nano

How much VRAM does GRaPE Nano need?

About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.5 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 GRaPE Nano on an 8 GB GPU?

Yes, with BF16: the 1.5 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GRaPE Nano GGUF?

It depends on the quant: Q2_K is 0.3 GB, Q4_K_M is 0.5 GB, Q6_K is 0.6 GB, BF16 is 1.5 GB.

What context length does GRaPE Nano support?

The GGUF header lists a trained context length of 128,000 tokens (125K). 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 GRaPE Nano GGUF?

The files are on Hugging Face in the SL-AI/GRaPE-Nano-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 GRaPE Nano 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.

Similar models

Browse all →

More from SL-AI

All by SL-AI →

More Grape models

All Grape →

Other tiny models

All tiny models →