Text Generation
GGUF
all use cases
creative
creative writing
all genres
tool calls
tool use
qwen3_moe
problem solving
deep thinking
reasoning
deep reasoning
story
writing
fiction
roleplaying
bfloat16
role play
sillytavern
backyard
Lmstudio
context 128k
Mixture of Experts
mixture of experts
8 experts activated
128 experts
NEO Imatrix
Max Imatrix
qwen3
imatrix
conversational
Update README.md
Browse files
README.md
CHANGED
|
@@ -84,8 +84,6 @@ These quants (all sizes) can be used on GPU AND/OR CPU (just CPU) due to unique
|
|
| 84 |
|
| 85 |
Activation of (8) experts is controlled automatically in the MOE structure of model and depends on prompt / input content.
|
| 86 |
|
| 87 |
-
Additional versions featuring 4, 12, 16 and 24 activated experts will follow shortly at separate repos.
|
| 88 |
-
|
| 89 |
TWO example generations included below, more to be added.
|
| 90 |
|
| 91 |
<B>IQ1_M MAX / IQ1_M MAX PLUS and Higher Quants:</B>
|
|
|
|
| 84 |
|
| 85 |
Activation of (8) experts is controlled automatically in the MOE structure of model and depends on prompt / input content.
|
| 86 |
|
|
|
|
|
|
|
| 87 |
TWO example generations included below, more to be added.
|
| 88 |
|
| 89 |
<B>IQ1_M MAX / IQ1_M MAX PLUS and Higher Quants:</B>
|