Commit
•
c230171
1
Parent(s):
d46474e
auto-patch README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ tags:
|
|
20 |
static quants of https://huggingface.co/ChaoticNeutrals/T-1000-8B
|
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
|
@@ -34,12 +34,17 @@ more details, including on how to concatenate multi-part files.
|
|
34 |
| Link | Type | Size/GB | Notes |
|
35 |
|:-----|:-----|--------:|:------|
|
36 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q2_K.gguf) | Q2_K | 3.3 | |
|
|
|
37 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.IQ3_M.gguf) | IQ3_M | 3.9 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
|
|
|
42 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
|
|
|
|
|
|
|
43 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
|
|
|
20 |
static quants of https://huggingface.co/ChaoticNeutrals/T-1000-8B
|
21 |
|
22 |
<!-- provided-files -->
|
23 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/T-1000-8B-i1-GGUF
|
24 |
## Usage
|
25 |
|
26 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
34 |
| Link | Type | Size/GB | Notes |
|
35 |
|:-----|:-----|--------:|:------|
|
36 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q2_K.gguf) | Q2_K | 3.3 | |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.IQ3_M.gguf) | IQ3_M | 3.9 | |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
|
48 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
|
50 |
| [GGUF](https://huggingface.co/mradermacher/T-1000-8B-GGUF/resolve/main/T-1000-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
|