Hugging Face's logo

mradermacher
/
CausalLM-RP-34B-GGUF

Transformers
GGUF
English
Not-For-All-Audiences
nsfw
Inference Endpoints
conversational
Model card Files Community
1
mradermacher commited on
Commit
9ffd74d
•
1 Parent(s): 510e2e1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -37,14 +37,13 @@ more details, including on how to concatenate multi-part files.
37
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.IQ4_XS.gguf) | IQ4_XS | 19.3 | |
38
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q4_0.gguf) | Q4_0 | 20.1 | fast, low quality |
39
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q4_K_S.gguf) | Q4_K_S | 20.2 | fast, recommended |
40
- | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.IQ4_NL.gguf) | IQ4_NL | 20.3 | slightly worse than Q4_K_S |
41
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q4_K_M.gguf) | Q4_K_M | 21.3 | fast, recommended |
42
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q5_K_S.gguf) | Q5_K_S | 24.3 | |
43
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q5_K_M.gguf) | Q5_K_M | 25.0 | |
44
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q6_K.gguf) | Q6_K | 28.9 | very good quality |
45
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q8_0.gguf) | Q8_0 | 37.1 | fast, best quality |
46
 
47
-
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
50
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.IQ4_XS.gguf) | IQ4_XS | 19.3 | |
38
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q4_0.gguf) | Q4_0 | 20.1 | fast, low quality |
39
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q4_K_S.gguf) | Q4_K_S | 20.2 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.IQ4_NL.gguf) | IQ4_NL | 20.3 | prefer IQ4_XS |
41
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q4_K_M.gguf) | Q4_K_M | 21.3 | fast, recommended |
42
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q5_K_S.gguf) | Q5_K_S | 24.3 | |
43
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q5_K_M.gguf) | Q5_K_M | 25.0 | |
44
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q6_K.gguf) | Q6_K | 28.9 | very good quality |
45
  | [GGUF](https://huggingface.co/mradermacher/CausalLM-RP-34B-GGUF/resolve/main/CausalLM-RP-34B.Q8_0.gguf) | Q8_0 | 37.1 | fast, best quality |
46
 
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
49