Hugging Face's logo

mradermacher
/
Llama-3.1-8B-exchange-v2-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
81c8148
·
verified ·
1 Parent(s): 6775335

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -30,7 +30,16 @@ more details, including on how to concatenate multi-part files.
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q2_K.gguf) | Q2_K | 3.3 | |
 
 
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
 
 
 
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
35
 
36
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q2_K.gguf) | Q2_K | 3.3 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
35
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
38
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
39
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-exchange-v2-GGUF/resolve/main/Llama-3.1-8B-exchange-v2.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
44
 
45
  Here is a handy graph by ikawrakow comparing some lower-quality quant