Hugging Face's logo

mradermacher
/
Falcon3-3B-Base-GGUF

Transformers
GGUF
falcon3
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
cde6e66
·
verified ·
1 Parent(s): 9c2831f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -40,10 +40,14 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q3_K_L.gguf) | Q3_K_L | 1.9 | |
 
43
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended |
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q6_K.gguf) | Q6_K | 2.8 | very good quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality |
 
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
 
40
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q3_K_L.gguf) | Q3_K_L | 1.9 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.IQ4_XS.gguf) | IQ4_XS | 1.9 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q5_K_S.gguf) | Q5_K_S | 2.4 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q5_K_M.gguf) | Q5_K_M | 2.4 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q6_K.gguf) | Q6_K | 2.8 | very good quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Base-GGUF/resolve/main/Falcon3-3B-Base.f16.gguf) | f16 | 6.6 | 16 bpw, overkill |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):