mradermacher commited on
Commit
c64f85e
·
verified ·
1 Parent(s): 23ee024

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -36,7 +36,27 @@ more details, including on how to concatenate multi-part files.
36
 
37
  | Link | Type | Size/GB | Notes |
38
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
39
  | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q2_K.gguf) | i1-Q2_K | 29.9 | IQ3_XXS probably better |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant
42
  types (lower is better):
 
36
 
37
  | Link | Type | Size/GB | Notes |
38
  |:-----|:-----|--------:|:------|
39
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ1_S.gguf) | i1-IQ1_S | 22.8 | for the desperate |
40
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ1_M.gguf) | i1-IQ1_M | 23.8 | mostly desperate |
41
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 25.6 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ2_XS.gguf) | i1-IQ2_XS | 27.2 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ2_S.gguf) | i1-IQ2_S | 28.0 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ2_M.gguf) | i1-IQ2_M | 29.4 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q2_K.gguf) | i1-Q2_K | 29.9 | IQ3_XXS probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 31.9 | lower quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ3_XS.gguf) | i1-IQ3_XS | 32.9 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ3_S.gguf) | i1-IQ3_S | 34.6 | beats Q3_K* |
49
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q3_K_S.gguf) | i1-Q3_K_S | 34.6 | IQ3_XS probably better |
50
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ3_M.gguf) | i1-IQ3_M | 35.6 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q3_K_M.gguf) | i1-Q3_K_M | 37.8 | IQ3_S probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q3_K_L.gguf) | i1-Q3_K_L | 39.6 | IQ3_M probably better |
53
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-IQ4_XS.gguf) | i1-IQ4_XS | 39.8 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q4_0.gguf) | i1-Q4_0 | 41.5 | fast, low quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q4_K_S.gguf) | i1-Q4_K_S | 44.0 | optimal size/speed/quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q4_K_M.gguf) | i1-Q4_K_M | 47.5 | fast, recommended |
57
+ | [PART 1](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 51.5 | |
58
+ | [PART 1](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 54.5 | |
59
+ | [PART 1](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Athene-V2-Agent-i1-GGUF/resolve/main/Athene-V2-Agent.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 64.4 | practically like static Q6_K |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant
62
  types (lower is better):