mradermacher commited on
Commit
54c1693
·
verified ·
1 Parent(s): 0c459bb

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -31,21 +31,27 @@ more details, including on how to concatenate multi-part files.
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
 
34
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ1_M.gguf) | i1-IQ1_M | 7.8 | mostly desperate |
35
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.7 | |
 
37
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.1 | very low quality |
38
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ2_M.gguf) | i1-IQ2_M | 11.3 | |
39
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q2_K.gguf) | i1-Q2_K | 12.1 | IQ3_XXS probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.4 | lower quality |
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.2 | IQ3_XS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ3_M.gguf) | i1-IQ3_M | 15.0 | |
43
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.9 | IQ3_S probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.4 | IQ3_M probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.4 | |
 
46
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.6 | optimal size/speed/quality |
47
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.7 | fast, recommended |
48
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.5 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q6_K.gguf) | i1-Q6_K | 26.8 | practically like static Q6_K |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
+ | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ1_S.gguf) | i1-IQ1_S | 7.2 | for the desperate |
35
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ1_M.gguf) | i1-IQ1_M | 7.8 | mostly desperate |
36
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.8 | |
37
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.7 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
39
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.1 | very low quality |
40
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ2_M.gguf) | i1-IQ2_M | 11.3 | |
41
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q2_K.gguf) | i1-Q2_K | 12.1 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.4 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.4 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ3_S.gguf) | i1-IQ3_S | 14.2 | beats Q3_K* |
45
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.2 | IQ3_XS probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ3_M.gguf) | i1-IQ3_M | 15.0 | |
47
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.9 | IQ3_S probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.4 | IQ3_M probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.4 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q4_0.gguf) | i1-Q4_0 | 18.5 | fast, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.6 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.7 | fast, recommended |
53
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.5 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.1 | |
55
  | [GGUF](https://huggingface.co/mradermacher/airoboros-33b-gpt4-1.2-i1-GGUF/resolve/main/airoboros-33b-gpt4-1.2.i1-Q6_K.gguf) | i1-Q6_K | 26.8 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant