mradermacher
commited on
Commit
•
65df707
1
Parent(s):
8d56fef
auto-patch README.md
Browse files
README.md
CHANGED
@@ -33,6 +33,7 @@ more details, including on how to concatenate multi-part files.
|
|
33 |
|
34 |
| Link | Type | Size/GB | Notes |
|
35 |
|:-----|:-----|--------:|:------|
|
|
|
36 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 26.0 | mostly desperate |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 29.9 | |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 33.1 | |
|
@@ -40,14 +41,18 @@ more details, including on how to concatenate multi-part files.
|
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 37.5 | |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 41.3 | IQ3_XXS probably better |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 43.2 | lower quality |
|
|
|
|
|
43 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 48.6 | IQ3_XS probably better |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 49.8 | |
|
45 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 53.8 | IQ3_S probably better |
|
46 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 58.2 | IQ3_M probably better |
|
47 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 59.7 | |
|
|
|
48 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 63.6 | optimal size/speed/quality |
|
49 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 67.3 | fast, recommended |
|
50 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 76.7 | |
|
|
|
51 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 91.3 | practically like static Q6_K |
|
52 |
|
53 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
33 |
|
34 |
| Link | Type | Size/GB | Notes |
|
35 |
|:-----|:-----|--------:|:------|
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ1_S.gguf) | i1-IQ1_S | 23.7 | for the desperate |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 26.0 | mostly desperate |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 29.9 | |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 33.1 | |
|
|
|
41 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 37.5 | |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 41.3 | IQ3_XXS probably better |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 43.2 | lower quality |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 46.0 | |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ3_S.gguf) | i1-IQ3_S | 48.6 | beats Q3_K* |
|
46 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 48.6 | IQ3_XS probably better |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 49.8 | |
|
48 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 53.8 | IQ3_S probably better |
|
49 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 58.2 | IQ3_M probably better |
|
50 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 59.7 | |
|
51 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 63.2 | fast, low quality |
|
52 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 63.6 | optimal size/speed/quality |
|
53 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 67.3 | fast, recommended |
|
54 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 76.7 | |
|
55 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 78.9 | |
|
56 |
| [PART 1](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen1.5-110B-Chat-i1-GGUF/resolve/main/Qwen1.5-110B-Chat.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 91.3 | practically like static Q6_K |
|
57 |
|
58 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|