SA

Samantha big MoE i1

SamanthaGGUF by mradermacherUpdated 2025-12-04
Download on Hugging Face
Parameters108B
Context10240K
Layers—
Architecturellama4
Smallest quant0.1 GB
Quick answer

Samantha big MoE i1 needs about 40.2 GB of memory at IQ2_M (a 35.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 14 quants, from 0.1 GB to 47.5 GB (IQ3_M).

Samantha big MoE i1 is a 108B-parameter Samantha model in GGUF format, quantized by mradermacher. Its trained context length is 10240K tokens. The repository has 14 quant files, from 0.1 GB to 47.5 GB (IQ3_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 0.6 GB
Fits Get file →
IQ1_S22.2 GB 25.3 GB
Too big Get file →
IQ1_M24.6 GB 28.0 GB
Too big Get file →
IQ2_XXS28.6 GB 32.5 GB
Too big Get file →
IQ2_XS31.8 GB 36.1 GB
Too big Get file →
IQ2_S32.3 GB 36.7 GB
Too big Get file →
IQ2_M35.5 GB 40.2 GB
Too big Get file →
Q2_K_S37.0 GB 41.9 GB
Too big Get file →
Q2_K39.6 GB 44.8 GB
Too big Get file →
IQ3_XXS41.7 GB 47.2 GB
Too big Get file →
IQ3_XS44.3 GB 50.1 GB
Too big Get file →
Q3_K_S46.7 GB 52.8 GB
Too big Get file →
IQ3_S46.8 GB 52.9 GB
Too big Get file →
IQ3_M47.5 GB 53.7 GB
Too big Get file →

What GPU do you need for Samantha big MoE i1?

These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (0.1 GB file, about 0.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ1_M (24.6 GB file, about 28.0 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_XXS (41.7 GB file, about 47.2 GB in use).

Which Samantha big MoE i1 quant should you choose?

IQ2_M (35.5 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 the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama4
Parameters108B
Trained context10,485,760 tokens

Source

Quantized bymradermacher
FamilySamantha
Downloads (HF)291
Last updated2025-12-04

Frequently asked questions about Samantha big MoE i1

How much VRAM does Samantha big MoE i1 need?

About 40.2 GB at IQ2_M with an 8K context window. That is the 35.5 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 Samantha big MoE i1 on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Samantha big MoE i1 GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 22.2 GB, IQ1_M is 24.6 GB, IQ2_XXS is 28.6 GB, IQ2_XS is 31.8 GB, IQ2_S is 32.3 GB and 8 more.

What context length does Samantha big MoE i1 support?

The GGUF header lists a trained context length of 10,485,760 tokens (10240K).

Where can I download Samantha big MoE i1 GGUF?

The files are on Hugging Face in the mradermacher/Samantha-big-MoE-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other large models

All large models →