4.6 KiB
base_model, language, library_name, license, license_link, license_name, quantized_by, tags
| base_model | language | library_name | license | license_link | license_name | quantized_by | tags | |||
|---|---|---|---|---|---|---|---|---|---|---|
| TechxGenus/CodeGemma-2b |
|
transformers | other | https://ai.google.dev/gemma/terms | gemma-terms-of-use | mradermacher |
|
About
static quants of https://huggingface.co/TechxGenus/CodeGemma-2b
weighted/imatrix quants are available at https://huggingface.co/mradermacher/CodeGemma-2b-i1-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 |
|---|---|---|---|
| PART 1 PART 2 | Q2_K | 2.4 | |
| PART 1 PART 2 | Q3_K_S | 2.7 | |
| PART 1 PART 2 | Q3_K_M | 2.9 | lower quality |
| PART 1 PART 2 | Q3_K_L | 3.0 | |
| PART 1 PART 2 | IQ4_XS | 3.1 | |
| PART 1 PART 2 | Q4_0_4_4 | 3.2 | fast on arm, low quality |
| PART 1 PART 2 | Q4_K_S | 3.2 | fast, recommended |
| PART 1 PART 2 | Q4_K_M | 3.4 | fast, recommended |
| PART 1 PART 2 | Q5_K_S | 3.7 | |
| PART 1 PART 2 | Q5_K_M | 3.8 | |
| PART 1 PART 2 | Q6_K | 4.2 | very good quality |
| PART 1 PART 2 | Q8_0 | 5.4 | fast, best quality |
| PART 1 PART 2 | f16 | 10.1 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
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.