LU

LunarPass 2 i1

LunarpassGGUF by mradermacherUpdated 2025-01-28
Download on Hugging Face
Parameters4.73B
Context128K
Layers40
Architecturephi3
Smallest quant1.0 GB
Quick answer

LunarPass 2 i1 needs about 7.5 GB of memory at Q4_K_M (a 3.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 1.0 GB (IQ1_S) to 3.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 16.1 GB.

LunarPass 2 i1 is a 4.73B-parameter Lunarpass model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 24 quant files, from 1.0 GB (IQ1_S) to 3.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.0 GB 5.6 GB
Fits Get file →
IQ1_M1.1 GB 5.6 GB
Fits Get file →
IQ2_XXS1.3 GB 5.8 GB
Fits Get file →
IQ2_XS1.4 GB 5.9 GB
Fits Get file →
IQ2_S1.5 GB 6.0 GB
Fits Get file →
IQ2_M1.6 GB 6.1 GB
Fits Get file →
Q2_K_S1.6 GB 6.2 GB
Fits Get file →
Q2_K1.7 GB 6.3 GB
Fits Get file →
IQ3_XXS1.9 GB 6.4 GB
Fits Get file →
IQ3_XS2.0 GB 6.5 GB
Fits Get file →
IQ3_S2.1 GB 6.6 GB
Fits Get file →
Q3_K_S2.1 GB 6.6 GB
Fits Get file →
IQ3_M2.3 GB 6.8 GB
Fits Get file →
Q3_K_M2.4 GB 6.9 GB
Fits Get file →
IQ4_XS2.5 GB 7.1 GB
Fits Get file →
Q3_K_L2.6 GB 7.1 GB
Fits Get file →
IQ4_NL2.7 GB 7.2 GB
Tight Get file →
Q4_02.7 GB 7.2 GB
Tight Get file →
Q4_K_S2.7 GB 7.2 GB
Tight Get file →
Q4_K_M3.0 GB 7.5 GB
Tight Get file →
Q4_13.0 GB 7.5 GB
Tight Get file →
Q5_K_S3.3 GB 7.8 GB
Tight Get file →
Q5_K_M3.5 GB 8.0 GB
Too big Get file →
Q6_K3.9 GB 8.4 GB
Too big Get file →

What GPU do you need for LunarPass 2 i1?

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 IQ2_S (1.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (3.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (3.9 GB file, about 8.4 GB in use).

Which LunarPass 2 i1 quant should you choose?

Q4_K_M is the usual starting point for LunarPass 2 i1: it balances file size and quality well. Here it is a 3.0 GB file.

If memory is tight, the smallest file is IQ1_S at 1.0 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

Architecturephi3
Parameters4.73B
Layers40
Trained context131,072 tokens
KV cache (fp16)480 KB per token

Source

Quantized bymradermacher
FamilyLunarpass
Licenseapache-2.0
Downloads (HF)109
Last updated2025-01-28

Frequently asked questions about LunarPass 2 i1

How much VRAM does LunarPass 2 i1 need?

About 7.5 GB at Q4_K_M with an 8K context window. That is the 3.0 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 LunarPass 2 i1 on an 8 GB GPU?

Yes, with Q5_K_M: the 3.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LunarPass 2 i1 GGUF?

It depends on the quant: IQ1_S is 1.0 GB, IQ1_M is 1.1 GB, IQ2_XXS is 1.3 GB, IQ2_XS is 1.4 GB, IQ2_S is 1.5 GB, IQ2_M is 1.6 GB and 18 more.

What context length does LunarPass 2 i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.0 GB at 8K and 16.1 GB at 32K.

Where can I download LunarPass 2 i1 GGUF?

The files are on Hugging Face in the mradermacher/LunarPass-2-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 LunarPass 2 i1 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 LunarPass-2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Lunarpass models

All Lunarpass →

Other small models

All small models →