Hugging Face's logo

mradermacher
/
granite-34b-code-instruct-i1-GGUF

Transformers
GGUF
English
code
granite
Inference Endpoints
imatrix
conversational
Model card Files Community
granite-34b-code-instruct-i1-GGUF / README.md
mradermacher's picture
mradermacher
auto-patch README.md
c89881a verified
preview code
|
raw
history blame
5.61 kB
metadata
base_model: ibm-granite/granite-34b-code-instruct
datasets:
  - bigcode/commitpackft
  - TIGER-Lab/MathInstruct
  - meta-math/MetaMathQA
  - glaiveai/glaive-code-assistant-v3
  - glaive-function-calling-v2
  - bugdaryan/sql-create-context-instruction
  - garage-bAInd/Open-Platypus
  - nvidia/HelpSteer
language:
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - code
  - granite

About

weighted/imatrix quants of https://huggingface.co/ibm-granite/granite-34b-code-instruct

static quants are available at https://huggingface.co/mradermacher/granite-34b-code-instruct-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 7.5 for the desperate
GGUF i1-IQ1_M 8.1 mostly desperate
GGUF i1-IQ2_XXS 9.3
GGUF i1-IQ2_XS 10.2
GGUF i1-IQ2_S 10.9
GGUF i1-IQ2_M 11.8
GGUF i1-Q2_K 13.2 IQ3_XXS probably better
GGUF i1-IQ3_XXS 13.5 lower quality
GGUF i1-IQ3_XS 14.4
GGUF i1-IQ3_S 14.9 beats Q3_K*
GGUF i1-Q3_K_S 14.9 IQ3_XS probably better
GGUF i1-IQ3_M 16.0
GGUF i1-Q3_K_M 17.7 IQ3_S probably better
GGUF i1-IQ4_XS 18.3
GGUF i1-Q4_0 19.4 fast, low quality
GGUF i1-Q4_K_S 19.5 optimal size/speed/quality
GGUF i1-Q3_K_L 19.6 IQ3_M probably better
GGUF i1-Q4_K_M 21.5 fast, recommended
GGUF i1-Q5_K_S 23.5
GGUF i1-Q5_K_M 24.8
GGUF i1-Q6_K 27.9 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. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.