LL

Impish LLAMA 4B iMatrix

LlamaGGUF by SicariusSicariiStuffUpdated 2025-08-16
Download on Hugging Face
Parameters4.51B
Context128K
Layers32
Architecturellama
Smallest quant1.2 GB
Quick answer

Impish LLAMA 4B iMatrix needs about 3.3 GB of memory at IQ2_M (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.2 GB (IQ1_S) to 2.7 GB (IQ4_NL). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Impish LLAMA 4B iMatrix is a 4.51B-parameter Llama model in GGUF format, quantized by SicariusSicariiStuff. Its trained context length is 128K tokens. The repository has 12 quant files, from 1.2 GB (IQ1_S) to 2.7 GB (IQ4_NL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.2 GB 2.8 GB
Fits Get file →
IQ1_M1.3 GB 2.9 GB
Fits Get file →
IQ2_XXS1.4 GB 3.0 GB
Fits Get file →
IQ2_XS1.5 GB 3.1 GB
Fits Get file →
IQ2_S1.6 GB 3.2 GB
Fits Get file →
IQ2_M1.7 GB 3.3 GB
Fits Get file →
IQ3_XXS1.9 GB 3.5 GB
Fits Get file →
IQ3_XS2.0 GB 3.6 GB
Fits Get file →
IQ3_S2.1 GB 3.7 GB
Fits Get file →
IQ3_M2.2 GB 3.8 GB
Fits Get file →
IQ4_XS2.5 GB 4.1 GB
Fits Get file →
IQ4_NL2.7 GB 4.2 GB
Fits Get file →

What GPU do you need for Impish LLAMA 4B iMatrix?

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 IQ3_M (2.2 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_NL (2.7 GB file, about 4.2 GB in use).

Which Impish LLAMA 4B iMatrix quant should you choose?

IQ2_M (1.7 GB) is the middle option in this repository. 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.

If memory is tight, the smallest file is IQ1_S at 1.2 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

Architecturellama
Parameters4.51B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

FamilyLlama
Licenseapache-2.0
Downloads (HF)112
Last updated2025-08-16

Frequently asked questions about Impish LLAMA 4B iMatrix

How much VRAM does Impish LLAMA 4B iMatrix need?

About 3.3 GB at IQ2_M with an 8K context window. That is the 1.7 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 Impish LLAMA 4B iMatrix on an 8 GB GPU?

Yes, with IQ4_NL: the 2.7 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Impish LLAMA 4B iMatrix GGUF?

It depends on the quant: IQ1_S is 1.2 GB, IQ1_M is 1.3 GB, IQ2_XXS is 1.4 GB, IQ2_XS is 1.5 GB, IQ2_S is 1.6 GB, IQ2_M is 1.7 GB and 6 more.

What context length does Impish LLAMA 4B iMatrix support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Impish LLAMA 4B iMatrix GGUF?

The files are on Hugging Face in the SicariusSicariiStuff/Impish_LLAMA_4B_iMatrix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Impish LLAMA 4B iMatrix 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 Impish_LLAMA_4B

Similar models

Browse all →

More from SicariusSicariiStuff

All by SicariusSicariiStuff →

More Llama models

All Llama →

Other small models

All small models →