Transformers
GGUF
English
shining-valiant
shining-valiant-2
valiant
valiant-labs
llama
llama-3.1
llama-3.1-instruct
llama-3.1-instruct-70b
llama-3
llama-3-instruct
llama-3-instruct-70b
70b
science
physics
biology
chemistry
compsci
computer-science
engineering
logic
rationality
advanced
expert
technical
conversational
chat
instruct
Inference Endpoints
imatrix
Commit
•
1123fd7
1
Parent(s):
0b19187
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -62,16 +62,26 @@ more details, including on how to concatenate multi-part files.
|
|
| 62 |
|
| 63 |
| Link | Type | Size/GB | Notes |
|
| 64 |
|:-----|:-----|--------:|:------|
|
|
|
|
| 65 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
|
|
|
|
|
|
|
|
|
|
| 66 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
|
| 67 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
|
| 68 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
|
|
|
|
|
|
|
| 69 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
|
| 70 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
|
| 71 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
|
|
|
|
| 72 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
|
|
|
|
| 73 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
|
| 74 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
|
|
|
|
|
|
|
| 75 |
| [PART 1](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
|
| 76 |
|
| 77 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
|
| 62 |
|
| 63 |
| Link | Type | Size/GB | Notes |
|
| 64 |
|:-----|:-----|--------:|:------|
|
| 65 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
|
| 66 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
|
| 67 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
|
| 68 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
|
| 69 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
|
| 70 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
|
| 71 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
|
| 72 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
|
| 73 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
|
| 74 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ3_S.gguf) | i1-IQ3_S | 31.0 | beats Q3_K* |
|
| 75 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
|
| 76 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
|
| 77 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
|
| 78 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better |
|
| 79 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
|
| 80 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
|
| 81 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
|
| 82 |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
|
| 83 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
|
| 84 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
|
| 85 |
| [PART 1](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama3.1-70B-ShiningValiant2-i1-GGUF/resolve/main/Llama3.1-70B-ShiningValiant2.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
|
| 86 |
|
| 87 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|