Commit
•
9cf483a
1
Parent(s):
a536cc7
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -32,11 +32,27 @@ more details, including on how to concatenate multi-part files.
|
|
| 32 |
|
| 33 |
| Link | Type | Size/GB | Notes |
|
| 34 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
|
|
|
|
|
|
|
|
|
|
| 37 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
|
|
|
|
|
|
|
|
|
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 42 |
types (lower is better):
|
|
|
|
| 32 |
|
| 33 |
| Link | Type | Size/GB | Notes |
|
| 34 |
|:-----|:-----|--------:|:------|
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
|
| 38 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
|
| 41 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ3_S.gguf) | i1-IQ3_S | 31.0 | beats Q3_K* |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
|
| 46 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
|
| 47 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
|
| 48 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better |
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
|
| 50 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
|
| 51 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
|
| 52 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
|
| 53 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
|
| 54 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
|
| 55 |
+
| [PART 1](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-lorablated-70B-i1-GGUF/resolve/main/Llama-3.1-Nemotron-lorablated-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
|
| 56 |
|
| 57 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 58 |
types (lower is better):
|