Transformers
GGUF
English
reasoning
thinking
uncensored
gated
mixture of experts
Mixture of Experts
8x3B
Llama 3.2 MOE
128k context
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prosing
vivid writing
fiction
roleplaying
float32
swearing
rp
horror
mergekit
llama-3
llama-3.2
imatrix
conversational
auto-patch README.md
Browse files
README.md
CHANGED
@@ -74,6 +74,30 @@ more details, including on how to concatenate multi-part files.
|
|
74 |
| Link | Type | Size/GB | Notes |
|
75 |
|:-----|:-----|--------:|:------|
|
76 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
|
78 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
79 |
types (lower is better):
|
|
|
74 |
| Link | Type | Size/GB | Notes |
|
75 |
|:-----|:-----|--------:|:------|
|
76 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
|
77 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ1_S.gguf) | i1-IQ1_S | 4.2 | for the desperate |
|
78 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.6 | mostly desperate |
|
79 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.3 | |
|
80 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.8 | |
|
81 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ2_S.gguf) | i1-IQ2_S | 5.9 | |
|
82 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ2_M.gguf) | i1-IQ2_M | 6.4 | |
|
83 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 6.6 | very low quality |
|
84 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q2_K.gguf) | i1-Q2_K | 7.1 | IQ3_XXS probably better |
|
85 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.5 | lower quality |
|
86 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 7.9 | |
|
87 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ3_S.gguf) | i1-IQ3_S | 8.4 | beats Q3_K* |
|
88 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 8.4 | IQ3_XS probably better |
|
89 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ3_M.gguf) | i1-IQ3_M | 8.7 | |
|
90 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 9.1 | IQ3_S probably better |
|
91 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 9.7 | IQ3_M probably better |
|
92 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 10.1 | |
|
93 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 10.7 | prefer IQ4_XS |
|
94 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q4_0.gguf) | i1-Q4_0 | 10.7 | fast, low quality |
|
95 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 10.8 | optimal size/speed/quality |
|
96 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 11.4 | fast, recommended |
|
97 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q4_1.gguf) | i1-Q4_1 | 11.8 | |
|
98 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 12.9 | |
|
99 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 13.3 | |
|
100 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF/resolve/main/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B.i1-Q6_K.gguf) | i1-Q6_K | 15.3 | practically like static Q6_K |
|
101 |
|
102 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
103 |
types (lower is better):
|