mradermacher
commited on
Commit
•
fde797a
1
Parent(s):
ef860c3
auto-patch README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ tags:
|
|
20 |
static quants of https://huggingface.co/llmixer/BigWeave-v26-95b
|
21 |
|
22 |
<!-- provided-files -->
|
23 |
-
weighted/imatrix quants
|
24 |
## Usage
|
25 |
|
26 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -33,7 +33,16 @@ more details, including on how to concatenate multi-part files.
|
|
33 |
|
34 |
| Link | Type | Size/GB | Notes |
|
35 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
36 |
| [PART 1](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q4_K_S.gguf.part2of2) | Q4_K_S | 53.8 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
37 |
|
38 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
39 |
types (lower is better):
|
|
|
20 |
static quants of https://huggingface.co/llmixer/BigWeave-v26-95b
|
21 |
|
22 |
<!-- provided-files -->
|
23 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/BigWeave-v26-95b-i1-GGUF
|
24 |
## Usage
|
25 |
|
26 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
33 |
|
34 |
| Link | Type | Size/GB | Notes |
|
35 |
|:-----|:-----|--------:|:------|
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q2_K.gguf) | Q2_K | 34.9 | |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q3_K_S.gguf) | Q3_K_S | 40.9 | |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q3_K_M.gguf) | Q3_K_M | 45.6 | lower quality |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q3_K_L.gguf) | Q3_K_L | 49.7 | |
|
40 |
| [PART 1](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q4_K_S.gguf.part2of2) | Q4_K_S | 53.8 | fast, recommended |
|
41 |
+
| [PART 1](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q4_K_M.gguf.part2of2) | Q4_K_M | 56.8 | fast, recommended |
|
42 |
+
| [PART 1](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q5_K_S.gguf.part2of2) | Q5_K_S | 65.2 | |
|
43 |
+
| [PART 1](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q5_K_M.gguf.part2of2) | Q5_K_M | 67.0 | |
|
44 |
+
| [PART 1](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q6_K.gguf.part2of2) | Q6_K | 77.7 | very good quality |
|
45 |
+
| [PART 1](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/BigWeave-v26-95b-GGUF/resolve/main/BigWeave-v26-95b.Q8_0.gguf.part3of3) | Q8_0 | 100.7 | fast, best quality |
|
46 |
|
47 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
48 |
types (lower is better):
|