mradermacher
commited on
Commit
•
a42e74b
1
Parent(s):
d5a315a
auto-patch README.md
Browse files
README.md
CHANGED
@@ -25,12 +25,16 @@ more details, including on how to concatenate multi-part files.
|
|
25 |
|
26 |
| Link | Type | Size/GB | Notes |
|
27 |
|:-----|:-----|--------:|:------|
|
|
|
28 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 16.4 | IQ3_XXS probably better |
|
|
|
29 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 18.9 | IQ3_XS probably better |
|
30 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 20.7 | IQ3_S probably better |
|
31 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 22.2 | IQ3_M probably better |
|
32 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 24.4 | optimal size/speed/quality |
|
33 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 26.1 | fast, medium quality |
|
|
|
|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 35.1 | practically like static Q6_K |
|
35 |
|
36 |
|
|
|
25 |
|
26 |
| Link | Type | Size/GB | Notes |
|
27 |
|:-----|:-----|--------:|:------|
|
28 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 15.1 | |
|
29 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 16.4 | IQ3_XXS probably better |
|
30 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 17.0 | fast, lower quality |
|
31 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 18.9 | IQ3_XS probably better |
|
32 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 20.7 | IQ3_S probably better |
|
33 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 22.2 | IQ3_M probably better |
|
34 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 24.4 | optimal size/speed/quality |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 26.1 | fast, medium quality |
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 29.6 | |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 31.2 | |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF/resolve/main/falcon-40b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 35.1 | practically like static Q6_K |
|
39 |
|
40 |
|