Edit model card

About

weighted/imatrix quants of https://huggingface.co/cognitivecomputations/Samantha-120b

the weights were calculated using 164k semi-random english tokens.

static quants are available at https://huggingface.co/mradermacher/Samantha-120b-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF i1-IQ1_S 25.7 for the desperate
GGUF i1-IQ1_M 27.8 mostly desperate
GGUF i1-IQ2_XXS 32.2
GGUF i1-IQ2_XS 35.8
GGUF i1-IQ2_S 37.2
GGUF i1-IQ2_M 40.5
GGUF i1-Q2_K 44.6 IQ3_XXS probably better
GGUF i1-IQ3_XXS 47.3 lower quality
GGUF i1-IQ3_XS 49.3
PART 1 PART 2 i1-Q3_K_XS 49.3
PART 1 PART 2 i1-IQ3_S 52.1 beats Q3_K*
PART 1 PART 2 i1-Q3_K_S 52.2 IQ3_XS probably better
PART 1 PART 2 i1-IQ3_M 53.8
PART 1 PART 2 i1-Q3_K_M 58.2 IQ3_S probably better
PART 1 PART 2 i1-Q3_K_L 63.4 IQ3_M probably better
PART 1 PART 2 i1-IQ4_XS 64.3
PART 1 PART 2 i1-Q4_0 68.1 fast, low quality
PART 1 PART 2 i1-Q4_K_S 68.7 optimal size/speed/quality
PART 1 PART 2 i1-Q4_K_M 72.6 fast, recommended
PART 1 PART 2 i1-Q5_K_S 82.9
PART 1 PART 2 i1-Q5_K_M 85.1
PART 1 PART 2 i1-Q6_K 98.8 practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

Downloads last month
51
GGUF
Model size
120B params
Architecture
llama

1-bit

2-bit

3-bit

Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for mradermacher/Samantha-120b-i1-GGUF