Transformers
GGUF
English
Inference Endpoints
conversational
mradermacher commited on
Commit
1038eb7
1 Parent(s): 377fba8

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -31,21 +31,21 @@ more details, including on how to concatenate multi-part files.
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.Q2_K.gguf) | Q2_K | 3.1 | |
35
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.IQ3_XS.gguf) | IQ3_XS | 3.4 | |
36
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
37
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.IQ3_S.gguf) | IQ3_S | 3.6 | beats Q3_K* |
38
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.IQ3_M.gguf) | IQ3_M | 3.7 | |
39
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
40
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
41
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
42
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
43
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
44
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
45
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
46
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
47
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
48
- | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
49
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):
 
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.Q2_K.gguf) | Q2_K | 3.1 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.IQ3_XS.gguf) | IQ3_XS | 3.4 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.IQ3_S.gguf) | IQ3_S | 3.6 | beats Q3_K* |
38
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.IQ3_M.gguf) | IQ3_M | 3.7 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/Med-Qwen2-7B-GGUF/resolve/main/Med-Qwen2-7B.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
49
 
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):