Any-to-Any
Transformers
English
sponsor
buy me a coffee
projects
help
support
contact
partners
ggufs
moes
mixture of experts
source
custom
models by sort
FAQs
help docs
SOTA models
about us
Turbo Brilliance Systems
NEO Imatrix
source code
Brainstorm Adapter
Cold Fusion Training
Model merging
model tuning
unsloth
mergekit
llamacpp
Update README.md
Browse files
README.md
CHANGED
|
@@ -118,9 +118,12 @@ BY SORT - MODEL:
|
|
| 118 |
|
| 119 |
<img src="cannonball.webp" style="padding:0px;">
|
| 120 |
|
|
|
|
|
|
|
| 121 |
Qwen3.6 27B: The strongest, overall qwen ever beating all other Qwens in total operational power with over 2400 likes // 4 million+ total downloads
|
| 122 |
and has over 70 additional repos with additional quant types:
|
| 123 |
- https://huggingface.co/DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF
|
|
|
|
| 124 |
|
| 125 |
Qwen3.8 27B: The highest scoring Qwen in brute, raw intelligence, using Qwen 3.8's 3 new reasoning modes, plus token reduction (1/2 to 1/10) enhancements
|
| 126 |
and over 1600 likes + and 100+ additional quant repos:
|
|
@@ -137,6 +140,7 @@ Qwen3.6 40B: The 40B Monster, specializing in creative and research with 730+ li
|
|
| 137 |
|
| 138 |
Qwen3.5 9B: At just 9B parameters it beats most untuned 27B models in both intelligence (640 ARC-C) and performance, over 1000 likes, plus features 5 reasoning and 5 instruct modes (Qwen 3.8) too:
|
| 139 |
- https://huggingface.co/DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF
|
|
|
|
| 140 |
|
| 141 |
<B>For model specific issues/help/FAQ see:</B>
|
| 142 |
- https://huggingface.co/DavidAU
|
|
|
|
| 118 |
|
| 119 |
<img src="cannonball.webp" style="padding:0px;">
|
| 120 |
|
| 121 |
+
NOTE: Most models have benchmarks, and 3rd party benchmarks (at repo or in the community section)
|
| 122 |
+
|
| 123 |
Qwen3.6 27B: The strongest, overall qwen ever beating all other Qwens in total operational power with over 2400 likes // 4 million+ total downloads
|
| 124 |
and has over 70 additional repos with additional quant types:
|
| 125 |
- https://huggingface.co/DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF
|
| 126 |
+
- Benchmarks (spoiler: It beats everyone): https://blog.robai.net/27bevals/
|
| 127 |
|
| 128 |
Qwen3.8 27B: The highest scoring Qwen in brute, raw intelligence, using Qwen 3.8's 3 new reasoning modes, plus token reduction (1/2 to 1/10) enhancements
|
| 129 |
and over 1600 likes + and 100+ additional quant repos:
|
|
|
|
| 140 |
|
| 141 |
Qwen3.5 9B: At just 9B parameters it beats most untuned 27B models in both intelligence (640 ARC-C) and performance, over 1000 likes, plus features 5 reasoning and 5 instruct modes (Qwen 3.8) too:
|
| 142 |
- https://huggingface.co/DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF
|
| 143 |
+
- This is our office workhorse ; bullet proof, stable, fast and off the scale IQ to boot.
|
| 144 |
|
| 145 |
<B>For model specific issues/help/FAQ see:</B>
|
| 146 |
- https://huggingface.co/DavidAU
|