Hugging Face's logo

prithivMLmods
/
Open-Xi-Math-Preview-GGUF

Text Generation
Transformers
GGUF
English
qwen2
text-generation-inference
math
conversational
Model card Files
xet
Community
Open-Xi-Math-Preview-GGUF / README.md
prithivMLmods's picture
prithivMLmods
Update README.md
b2a18b4 verified
preview code
|
raw
history blame contribute delete
4.15 kB
metadata
license: apache-2.0
language:
  - en
base_model:
  - prithivMLmods/Open-Xi-Math-Preview
pipeline_tag: text-generation
library_name: transformers
tags:
  - text-generation-inference
  - math

Open-Xi-Math-Preview-GGUF

Open-Xi-Math-Preview is a mathematics-focused reasoning model fine-tuned on Qwen2-1.5B-Instruct, utilizing a modular dataset designed for enhancing mathematical thinking. It provides robust capabilities in symbolic reasoning, structured deduction, and compact coding — optimized for edge deployment on resource-constrained devices.

Model Files

File Name Size Quantization Format Description
Open-Xi-Math-Preview.BF16.gguf 3.56 GB BF16 GGUF BFloat16 precision version
Open-Xi-Math-Preview.F16.gguf 3.56 GB FP16 GGUF Float16 precision version
Open-Xi-Math-Preview.F32.gguf 7.11 GB FP32 GGUF Float32 precision version
Open-Xi-Math-Preview.Q2_K.gguf 753 MB Q2_K GGUF 2-bit quantized (K variant)
Open-Xi-Math-Preview.Q3_K_M.gguf 924 MB Q3_K_M GGUF 3-bit quantized (K M variant)
Open-Xi-Math-Preview.Q4_K_M.gguf 1.12 GB Q4_K_M GGUF 4-bit quantized (K M variant)
Open-Xi-Math-Preview.Q4_K_S.gguf 1.07 GB Q4_K_S GGUF 4-bit quantized (K S variant)
Open-Xi-Math-Preview.Q5_K_M.gguf 1.29 GB Q5_K_M GGUF 5-bit quantized (K M variant)
Open-Xi-Math-Preview.Q5_K_S.gguf 1.26 GB Q5_K_S GGUF 5-bit quantized (K S variant)
Open-Xi-Math-Preview.Q6_K.gguf 1.46 GB Q6_K GGUF 6-bit quantized (K variant)
Open-Xi-Math-Preview.Q8_0.gguf 1.89 GB Q8_0 GGUF 8-bit quantized
.gitattributes 2.39 kB — — Git LFS tracking file
config.json 31 B — — Configuration file
README.md 4.29 kB — — Model documentation

Quants Usage

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

Link Type Size/GB Notes
GGUF Q2_K 0.4
GGUF Q3_K_S 0.5
GGUF Q3_K_M 0.5 lower quality
GGUF Q3_K_L 0.5
GGUF IQ4_XS 0.6
GGUF Q4_K_S 0.6 fast, recommended
GGUF Q4_K_M 0.6 fast, recommended
GGUF Q5_K_S 0.6
GGUF Q5_K_M 0.7
GGUF Q6_K 0.7 very good quality
GGUF Q8_0 0.9 fast, best quality
GGUF f16 1.6 16 bpw, overkill

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

image.png