auto-patch README.md
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ tags:
|
|
22 |
static quants of https://huggingface.co/kromeurus/L3.1-Tivir-v0.1-10B
|
23 |
|
24 |
<!-- provided-files -->
|
25 |
-
weighted/imatrix quants
|
26 |
## Usage
|
27 |
|
28 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -36,7 +36,15 @@ more details, including on how to concatenate multi-part files.
|
|
36 |
| Link | Type | Size/GB | Notes |
|
37 |
|:-----|:-----|--------:|:------|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.Q2_K.gguf) | Q2_K | 4.2 | |
|
|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.Q3_K_M.gguf) | Q3_K_M | 5.4 | lower quality |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
|
41 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
42 |
types (lower is better):
|
|
|
22 |
static quants of https://huggingface.co/kromeurus/L3.1-Tivir-v0.1-10B
|
23 |
|
24 |
<!-- provided-files -->
|
25 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-i1-GGUF
|
26 |
## Usage
|
27 |
|
28 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
36 |
| Link | Type | Size/GB | Notes |
|
37 |
|:-----|:-----|--------:|:------|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.Q2_K.gguf) | Q2_K | 4.2 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.Q3_K_S.gguf) | Q3_K_S | 4.9 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.Q3_K_M.gguf) | Q3_K_M | 5.4 | lower quality |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.Q3_K_L.gguf) | Q3_K_L | 5.8 | |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.IQ4_XS.gguf) | IQ4_XS | 6.0 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.Q5_K_S.gguf) | Q5_K_S | 7.5 | |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.Q5_K_M.gguf) | Q5_K_M | 7.7 | |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.Q6_K.gguf) | Q6_K | 8.8 | very good quality |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/L3.1-Tivir-v0.1-10B-GGUF/resolve/main/L3.1-Tivir-v0.1-10B.f16.gguf) | f16 | 21.4 | 16 bpw, overkill |
|
48 |
|
49 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
50 |
types (lower is better):
|