Commit
•
b58f5ea
1
Parent(s):
380bfc1
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,6 @@ tags:
|
|
| 17 |
|
| 18 |
weighted/imatrix quants of https://huggingface.co/Undi95/MiquTotalMix-70B
|
| 19 |
|
| 20 |
-
|
| 21 |
<!-- provided-files -->
|
| 22 |
static quants are available at https://huggingface.co/mradermacher/MiquTotalMix-70B-GGUF
|
| 23 |
## Usage
|
|
@@ -33,7 +32,15 @@ more details, including on how to concatenate multi-part files.
|
|
| 33 |
| Link | Type | Size/GB | Notes |
|
| 34 |
|:-----|:-----|--------:|:------|
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
|
| 39 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
|
| 17 |
|
| 18 |
weighted/imatrix quants of https://huggingface.co/Undi95/MiquTotalMix-70B
|
| 19 |
|
|
|
|
| 20 |
<!-- provided-files -->
|
| 21 |
static quants are available at https://huggingface.co/mradermacher/MiquTotalMix-70B-GGUF
|
| 22 |
## Usage
|
|
|
|
| 32 |
| Link | Type | Size/GB | Notes |
|
| 33 |
|:-----|:-----|--------:|:------|
|
| 34 |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.3 | IQ3_XS probably better |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.6 | IQ3_M probably better |
|
| 38 |
+
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 37.2 | |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, recommended |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.9 | |
|
| 42 |
+
| [GGUF](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 49.2 | |
|
| 43 |
+
| [PART 1](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/MiquTotalMix-70B-i1-GGUF/resolve/main/MiquTotalMix-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 57.0 | practically like static Q6_K |
|
| 44 |
|
| 45 |
|
| 46 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|