Samantha GGUF models

89 GGUF models in the Samantha family, quantized by 15 uploaders. Sizes run from 1.1B to 120B parameters. The longest trained context is 10240K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
SA
Samantha Mythomax l2 13b merge fixed i1
Samantha · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
SA
Samantha v5 wizardlm2
Samantha · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SA
Dr.Samantha-8B
Samantha · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Samantha 1.11 70B
Samantha · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
SA
Samantha 1.11 13B
Samantha · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
SA
samantha 1.1 westlake 7b i1
Samantha · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SA
Dr.Samantha-8B
Samantha · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
SA
Dr.RP.Samantha-L3-8B
Samantha · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
SA
Samantha 1.1 70b i1
Samantha · mradermacher
Params69B
Context4K
Q4_K_M41.7 GB
GGUF
SA
samantha 1.1 westlake 7b
Samantha · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SA
Samantha 1.1 Westlake 7b
Samantha · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SA
sethuiyer_dr_samantha-7b
Samantha · TheBloke
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
SA
Samantha V2.0 i1
Samantha · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
SA
Samantha v6
Samantha · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
SA
Samantha 33b
Samantha · mradermacher
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
SA
samantha 1.1 MBX 7B i1
Samantha · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SA
Samantha 120b i1
Samantha · mradermacher
Params120B
Context4K
Smallest25.6 GB
GGUF
SA
samantha 1.1 MBX 7B
Samantha · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SA
Samantha 1.11 7b i1
Samantha · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
SA
Dr Samantha 7b i1
Samantha · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
SA
Samantha 1.1 70B
Samantha · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
SA
Dr.RP.Samantha-L3-8B
Samantha · mradermacher
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
SA
Samantha 1.11 13b i1
Samantha · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
SA
Samantha NSFW 27B Q4
Samantha · davemahoney69
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
SA
Samantha 3b Beta0.1 Model
Samantha · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
SA
Samantha big MoE i1
Samantha · mradermacher
Params108B
Context10240K
Smallest0.1 GB
GGUF
SA
Samantha 13b
Samantha · mradermacher
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
SA
Samantha 7b
Samantha · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
SA
Samantha Mythomax l2 13b merge fixed
Samantha · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
SA
Dr Samantha 7b
Samantha · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF

About the Samantha GGUF models

Samantha is represented on ggufmodels.com by 89 GGUF models, quantized by 15 uploaders on Hugging Face. The most downloaded are Samantha Mythomax l2 13b merge fixed i1, Samantha v5 wizardlm2 and Dr.Samantha-8B. Parameter counts run from 1.1B to 120B, and the longest trained context window is 10240K tokens.

A Q4_K_M file of a Samantha model is between 0.7 to 42.5 GB, which is the quant most people start with. Most files come from mradermacher (51), Guilherme34 (21) and TheBloke (4). The quants you will meet most often are Q4_K_M (69), Q2_K (66), Q5_K_M (60) and Q3_K_S (60), where the number is how many models offer that quant.

Frequently asked questions

Which Samantha GGUF should I download?

The most downloaded Samantha GGUF here is Samantha Mythomax l2 13b merge fixed i1. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Samantha model need?

Q4_K_M files of Samantha models on this site range from 0.7 to 42.5 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Samantha GGUF files come from?

The most common quantizers here are mradermacher, Guilherme34 and TheBloke. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing