Hugging Face's logo

mradermacher
/
ReWiz-Qwen-2.5-14B-GGUF

Transformers
GGUF
English
text-generation-inference
unsloth
qwen2
trl
sft
theprint
rewiz
Inference Endpoints
Model card Files Community
1
mradermacher commited on
Commit
2f42da0
•
1 Parent(s): 5d86d3a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -27,7 +27,7 @@ tags:
27
  static quants of https://huggingface.co/theprint/ReWiz-Qwen-2.5-14B
28
 
29
  <!-- provided-files -->
30
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
31
  ## Usage
32
 
33
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -40,18 +40,18 @@ more details, including on how to concatenate multi-part files.
40
 
41
  | Link | Type | Size/GB | Notes |
42
  |:-----|:-----|--------:|:------|
43
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q2_K.gguf) | Q2_K | 11.6 | |
44
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q3_K_S.gguf) | Q3_K_S | 13.4 | |
45
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q3_K_M.gguf) | Q3_K_M | 14.8 | lower quality |
46
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q3_K_L.gguf) | Q3_K_L | 15.9 | |
47
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.IQ4_XS.gguf) | IQ4_XS | 16.5 | |
48
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q4_0_4_4.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q4_0_4_4.gguf) | Q4_0_4_4 | 17.1 | fast on arm, low quality |
49
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q4_K_S.gguf) | Q4_K_S | 17.2 | fast, recommended |
50
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q4_K_M.gguf) | Q4_K_M | 18.1 | fast, recommended |
51
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q5_K_S.gguf) | Q5_K_S | 20.6 | |
52
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q5_K_M.gguf) | Q5_K_M | 21.1 | |
53
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q6_K.gguf) | Q6_K | 24.3 | very good quality |
54
- | [PART 1](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q8_0.gguf) | Q8_0 | 31.5 | fast, best quality |
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
57
  types (lower is better):
 
27
  static quants of https://huggingface.co/theprint/ReWiz-Qwen-2.5-14B
28
 
29
  <!-- provided-files -->
30
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-i1-GGUF
31
  ## Usage
32
 
33
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
40
 
41
  | Link | Type | Size/GB | Notes |
42
  |:-----|:-----|--------:|:------|
43
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q2_K.gguf) | Q2_K | 11.6 | |
44
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q3_K_S.gguf) | Q3_K_S | 13.4 | |
45
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q3_K_M.gguf) | Q3_K_M | 14.8 | lower quality |
46
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q3_K_L.gguf) | Q3_K_L | 15.9 | |
47
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.IQ4_XS.gguf) | IQ4_XS | 16.5 | |
48
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q4_0_4_4.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q4_0_4_4.gguf) | Q4_0_4_4 | 17.1 | fast on arm, low quality |
49
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q4_K_S.gguf) | Q4_K_S | 17.2 | fast, recommended |
50
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q4_K_M.gguf) | Q4_K_M | 18.1 | fast, recommended |
51
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q5_K_S.gguf) | Q5_K_S | 20.6 | |
52
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q5_K_M.gguf) | Q5_K_M | 21.1 | |
53
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q6_K.gguf) | Q6_K | 24.3 | very good quality |
54
+ | [PART 1](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF/resolve/main/rewiz-qwen-2.5-14b.Q8_0.gguf) | Q8_0 | 31.5 | fast, best quality |
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
57
  types (lower is better):