Hugging Face's logo

mradermacher
/
internlm3-8b-instruct-i1-GGUF

Transformers
GGUF
English
imatrix
conversational
Model card Files
xet
 Community
mradermacher commited on
Commit
ac26557
·
verified ·
1 Parent(s): 95a9b71

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -29,10 +29,30 @@ more details, including on how to concatenate multi-part files.
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
32
  | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.6 | IQ3_XXS probably better |
33
  | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.7 | lower quality |
 
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 4.2 | |
 
 
 
 
 
35
  | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.2 | optimal size/speed/quality |
 
 
 
 
 
36
 
37
  Here is a handy graph by ikawrakow comparing some lower-quality quant
38
  types (lower is better):
 
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.3 | for the desperate |
33
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate |
34
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.7 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.9 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 3.1 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 3.3 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.3 | very low quality |
39
  | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.6 | IQ3_XXS probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.7 | lower quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.9 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.1 | IQ3_XS probably better |
43
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 4.1 | beats Q3_K* |
44
  | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 4.2 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.5 | IQ3_S probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.8 | IQ3_M probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.9 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 5.2 | prefer IQ4_XS |
49
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 5.2 | fast, low quality |
50
  | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.2 | optimal size/speed/quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.5 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q4_1.gguf) | i1-Q4_1 | 5.7 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.2 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.4 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/internlm3-8b-instruct-i1-GGUF/resolve/main/internlm3-8b-instruct.i1-Q6_K.gguf) | i1-Q6_K | 7.3 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant
58
  types (lower is better):