DavidAU commited on
Commit
f1628a7
·
verified ·
1 Parent(s): 5319994

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -30,9 +30,9 @@ tags:
30
  - mixture of experts
31
  - 128 experts
32
  - 8 active experts
33
- - 1 million context
34
  - qwen3
35
- - finetune
36
  - brainstorm 20x
37
  - brainstorm
38
  - optional thinking
@@ -128,7 +128,10 @@ QUANTS
128
 
129
  ---
130
 
131
- Quants are build using NEO Imatrix dataset, and optimized specifically for thinking block models with the output tensor at 16 bits.
 
 
 
132
 
133
  ---
134
 
 
30
  - mixture of experts
31
  - 128 experts
32
  - 8 active experts
33
+ - 256k context
34
  - qwen3
35
+ - gguf
36
  - brainstorm 20x
37
  - brainstorm
38
  - optional thinking
 
128
 
129
  ---
130
 
131
+ Quants are build using NEO Imatrix dataset (by DavidAU), and optimized specifically for thinking block models
132
+ with the output tensor at 16 bits.
133
+
134
+ I have found this specific combo to be unbeatable even at IQ2_M.
135
 
136
  ---
137