mradermacher commited on
Commit
165108d
·
verified ·
1 Parent(s): 995431d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -63,10 +63,12 @@ more details, including on how to concatenate multi-part files.
63
  |:-----|:-----|--------:|:------|
64
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
65
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ1_S.gguf) | i1-IQ1_S | 7.1 | for the desperate |
 
66
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
67
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
68
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ2_S.gguf) | i1-IQ2_S | 10.2 | |
69
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ2_M.gguf) | i1-IQ2_M | 11.2 | |
 
70
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.7 | IQ3_XS probably better |
71
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ3_S.gguf) | i1-IQ3_S | 14.7 | beats Q3_K* |
72
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.6 | IQ3_M probably better |
@@ -74,6 +76,7 @@ more details, including on how to concatenate multi-part files.
74
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.5 | fast, recommended |
75
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.3 | |
76
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q5_K_M.gguf) | i1-Q5_K_M | 24.0 | |
 
77
 
78
  Here is a handy graph by ikawrakow comparing some lower-quality quant
79
  types (lower is better):
 
63
  |:-----|:-----|--------:|:------|
64
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
65
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ1_S.gguf) | i1-IQ1_S | 7.1 | for the desperate |
66
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ1_M.gguf) | i1-IQ1_M | 7.8 | mostly desperate |
67
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
68
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
69
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ2_S.gguf) | i1-IQ2_S | 10.2 | |
70
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ2_M.gguf) | i1-IQ2_M | 11.2 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.1 | lower quality |
72
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.7 | IQ3_XS probably better |
73
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-IQ3_S.gguf) | i1-IQ3_S | 14.7 | beats Q3_K* |
74
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.6 | IQ3_M probably better |
 
76
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.5 | fast, recommended |
77
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.3 | |
78
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q5_K_M.gguf) | i1-Q5_K_M | 24.0 | |
79
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-i1-GGUF/resolve/main/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill.i1-Q6_K.gguf) | i1-Q6_K | 27.7 | practically like static Q6_K |
80
 
81
  Here is a handy graph by ikawrakow comparing some lower-quality quant
82
  types (lower is better):