Hugging Face's logo

mradermacher
/
LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF

Transformers
GGUF
English
dllm
diffusion
llm
text_generation
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
3045abd
·
verified ·
1 Parent(s): 82315b3

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -43,22 +43,29 @@ more details, including on how to concatenate multi-part files.
43
  | Link | Type | Size/GB | Notes |
44
  |:-----|:-----|--------:|:------|
45
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
46
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ1_M.gguf) | i1-IQ1_M | 2.0 | mostly desperate |
47
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.2 | |
48
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.4 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ2_M.gguf) | i1-IQ2_M | 2.7 | |
50
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.7 | very low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q2_K.gguf) | i1-Q2_K | 2.9 | IQ3_XXS probably better |
52
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.0 | lower quality |
 
 
53
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.4 | IQ3_XS probably better |
54
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ3_M.gguf) | i1-IQ3_M | 3.5 | |
55
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.7 | IQ3_S probably better |
56
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.0 | IQ3_M probably better |
57
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.1 | |
58
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.3 | prefer IQ4_XS |
 
59
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.4 | optimal size/speed/quality |
60
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.6 | fast, recommended |
 
61
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.2 | |
 
62
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q6_K.gguf) | i1-Q6_K | 6.1 | practically like static Q6_K |
63
 
64
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
43
  | Link | Type | Size/GB | Notes |
44
  |:-----|:-----|--------:|:------|
45
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
46
+ | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ1_S.gguf) | i1-IQ1_S | 1.8 | for the desperate |
47
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ1_M.gguf) | i1-IQ1_M | 2.0 | mostly desperate |
48
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.2 | |
49
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.4 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ2_S.gguf) | i1-IQ2_S | 2.5 | |
51
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ2_M.gguf) | i1-IQ2_M | 2.7 | |
52
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.7 | very low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q2_K.gguf) | i1-Q2_K | 2.9 | IQ3_XXS probably better |
54
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.0 | lower quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.2 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ3_S.gguf) | i1-IQ3_S | 3.4 | beats Q3_K* |
57
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.4 | IQ3_XS probably better |
58
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ3_M.gguf) | i1-IQ3_M | 3.5 | |
59
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.7 | IQ3_S probably better |
60
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.0 | IQ3_M probably better |
61
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.1 | |
62
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.3 | prefer IQ4_XS |
63
+ | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q4_0.gguf) | i1-Q4_0 | 4.4 | fast, low quality |
64
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.4 | optimal size/speed/quality |
65
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.6 | fast, recommended |
66
+ | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q4_1.gguf) | i1-Q4_1 | 4.8 | |
67
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.2 | |
68
+ | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.4 | |
69
  | [GGUF](https://huggingface.co/mradermacher/LLaDA-MoE-7B-A1B-Instruct-TD-i1-GGUF/resolve/main/LLaDA-MoE-7B-A1B-Instruct-TD.i1-Q6_K.gguf) | i1-Q6_K | 6.1 | practically like static Q6_K |
70
 
71
  Here is a handy graph by ikawrakow comparing some lower-quality quant