auto-patch README.md

README.md

@@ -5,7 +5,7 @@ language:
 - en
 library_name: transformers
 license: apache-2.0
-no_imatrix: "GGML_ASSERT: llama.cpp/ggml-quants.c:11239: grid_index >= 0"
+no_imatrix: 'GGML_ASSERT: llama.cpp/ggml-quants.c:11239: grid_index >= 0'
 quantized_by: mradermacher
 tags:
 - text-generation-inference
@@ -40,6 +40,7 @@ more details, including on how to concatenate multi-part files.
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-i1-GGUF/resolve/main/llama-3-70B-instruct-uncensored.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-i1-GGUF/resolve/main/llama-3-70B-instruct-uncensored.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
 | [GGUF](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-i1-GGUF/resolve/main/llama-3-70B-instruct-uncensored.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
 | [PART 1](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-i1-GGUF/resolve/main/llama-3-70B-instruct-uncensored.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-i1-GGUF/resolve/main/llama-3-70B-instruct-uncensored.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |