Hugging Face's logo

mradermacher
/
Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF

Transformers
GGUF
Inference Endpoints
imatrix
Model card Files Community
1
mradermacher commited on
Commit
800d58b
·
verified ·
1 Parent(s): 2b7d28d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -0
README.md CHANGED
@@ -52,14 +52,28 @@ more details, including on how to concatenate multi-part files.
52
 
53
  | Link | Type | Size/GB | Notes |
54
  |:-----|:-----|--------:|:------|
 
 
 
 
 
55
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ2_M.gguf) | i1-IQ2_M | 8.2 | |
 
56
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q2_K.gguf) | i1-Q2_K | 9.0 | IQ3_XXS probably better |
57
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality |
 
 
 
58
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ3_M.gguf) | i1-IQ3_M | 10.8 | |
59
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.6 | IQ3_S probably better |
 
60
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.9 | |
 
61
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.6 | optimal size/speed/quality |
62
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.4 | fast, recommended |
 
 
 
63
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q6_K.gguf) | i1-Q6_K | 19.4 | practically like static Q6_K |
64
 
65
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
52
 
53
  | Link | Type | Size/GB | Notes |
54
  |:-----|:-----|--------:|:------|
55
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ1_S.gguf) | i1-IQ1_S | 5.4 | for the desperate |
56
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ1_M.gguf) | i1-IQ1_M | 5.9 | mostly desperate |
57
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.6 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.3 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ2_S.gguf) | i1-IQ2_S | 7.6 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ2_M.gguf) | i1-IQ2_M | 8.2 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.4 | very low quality |
62
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q2_K.gguf) | i1-Q2_K | 9.0 | IQ3_XXS probably better |
63
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality |
64
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.0 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better |
66
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ3_S.gguf) | i1-IQ3_S | 10.5 | beats Q3_K* |
67
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ3_M.gguf) | i1-IQ3_M | 10.8 | |
68
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.6 | IQ3_S probably better |
69
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.5 | IQ3_M probably better |
70
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.9 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q4_0.gguf) | i1-Q4_0 | 13.6 | fast, low quality |
72
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.6 | optimal size/speed/quality |
73
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.4 | fast, recommended |
74
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q4_1.gguf) | i1-Q4_1 | 15.0 | |
75
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.4 | |
76
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q5_K_M.gguf) | i1-Q5_K_M | 16.9 | |
77
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Instruct-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Instruct-2503.i1-Q6_K.gguf) | i1-Q6_K | 19.4 | practically like static Q6_K |
78
 
79
  Here is a handy graph by ikawrakow comparing some lower-quality quant