mradermacher commited on
Commit
7fc7aec
1 Parent(s): c3529ed

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -32,13 +32,17 @@ more details, including on how to concatenate multi-part files.
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q2_K.gguf) | Q2_K | 2.6 | |
 
35
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.IQ3_S.gguf) | IQ3_S | 3.1 | beats Q3_K* |
36
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q3_K_S.gguf) | Q3_K_S | 3.1 | |
37
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.IQ3_M.gguf) | IQ3_M | 3.2 | |
38
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
 
 
42
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
43
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
44
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q2_K.gguf) | Q2_K | 2.6 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.IQ3_XS.gguf) | IQ3_XS | 2.9 | |
36
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.IQ3_S.gguf) | IQ3_S | 3.1 | beats Q3_K* |
37
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q3_K_S.gguf) | Q3_K_S | 3.1 | |
38
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.IQ3_M.gguf) | IQ3_M | 3.2 | |
39
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
40
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
42
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
43
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
46
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
47
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
48
  | [GGUF](https://huggingface.co/mradermacher/deepseek-coder-6.7b-base-GGUF/resolve/main/deepseek-coder-6.7b-base.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |