Hugging Face's logo

mradermacher
/
Qwen2.5-0.5B-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
4b91973
·
verified ·
1 Parent(s): 193517e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -31,17 +31,25 @@ more details, including on how to concatenate multi-part files.
31
  | Link | Type | Size/GB | Notes |
32
  |:-----|:-----|--------:|:------|
33
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q3_K_S.gguf) | Q3_K_S | 0.4 | |
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q2_K.gguf) | Q2_K | 0.4 | |
 
35
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.IQ4_XS.gguf) | IQ4_XS | 0.5 | |
 
36
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.5 | fast on arm, low quality |
37
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality |
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q3_K_L.gguf) | Q3_K_L | 0.5 | |
 
39
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended |
 
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q5_K_S.gguf) | Q5_K_S | 0.5 | |
 
42
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q5_K_M.gguf) | Q5_K_M | 0.5 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q6_K.gguf) | Q6_K | 0.6 | very good quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality |
 
45
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.f16.gguf) | f16 | 1.1 | 16 bpw, overkill |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
31
  | Link | Type | Size/GB | Notes |
32
  |:-----|:-----|--------:|:------|
33
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q3_K_S.gguf) | Q3_K_S | 0.4 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.IQ3_S.gguf) | IQ3_S | 0.4 | beats Q3_K* |
35
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.IQ3_XS.gguf) | IQ3_XS | 0.4 | |
36
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q2_K.gguf) | Q2_K | 0.4 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.IQ3_M.gguf) | IQ3_M | 0.4 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.IQ4_XS.gguf) | IQ4_XS | 0.5 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q4_0.gguf) | Q4_0 | 0.5 | fast, low quality |
40
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.5 | fast on arm, low quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q3_K_L.gguf) | Q3_K_L | 0.5 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q4_1.gguf) | Q4_1 | 0.5 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q5_0.gguf) | Q5_0 | 0.5 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended |
47
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q5_K_S.gguf) | Q5_K_S | 0.5 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q5_1.gguf) | Q5_1 | 0.5 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q5_K_M.gguf) | Q5_K_M | 0.5 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q6_K.gguf) | Q6_K | 0.6 | very good quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.bf16.gguf) | bf16 | 1.1 | 16 bpw, overkill |
53
  | [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-GGUF/resolve/main/Qwen2.5-0.5B.f16.gguf) | f16 | 1.1 | 16 bpw, overkill |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant