mradermacher commited on
Commit
c1dc390
·
verified ·
1 Parent(s): d49d964

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -1
README.md CHANGED
@@ -48,7 +48,7 @@ static quants of https://huggingface.co/DavidAU/Qwen3-Code-Reasoning-Instruct-6B
48
 
49
  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF).***
50
 
51
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
52
  ## Usage
53
 
54
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -64,9 +64,15 @@ more details, including on how to concatenate multi-part files.
64
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q2_K.gguf) | Q2_K | 2.5 | |
65
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q3_K_S.gguf) | Q3_K_S | 2.8 | |
66
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q3_K_M.gguf) | Q3_K_M | 3.1 | lower quality |
 
 
67
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q4_K_S.gguf) | Q4_K_S | 3.6 | fast, recommended |
 
 
 
68
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q6_K.gguf) | Q6_K | 5.0 | very good quality |
69
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q8_0.gguf) | Q8_0 | 6.4 | fast, best quality |
 
70
 
71
  Here is a handy graph by ikawrakow comparing some lower-quality quant
72
  types (lower is better):
 
48
 
49
  ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF).***
50
 
51
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-i1-GGUF
52
  ## Usage
53
 
54
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
64
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q2_K.gguf) | Q2_K | 2.5 | |
65
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q3_K_S.gguf) | Q3_K_S | 2.8 | |
66
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q3_K_M.gguf) | Q3_K_M | 3.1 | lower quality |
67
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q3_K_L.gguf) | Q3_K_L | 3.4 | |
68
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.IQ4_XS.gguf) | IQ4_XS | 3.4 | |
69
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q4_K_S.gguf) | Q4_K_S | 3.6 | fast, recommended |
70
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q4_K_M.gguf) | Q4_K_M | 3.7 | fast, recommended |
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q5_K_S.gguf) | Q5_K_S | 4.2 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q5_K_M.gguf) | Q5_K_M | 4.3 | |
73
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q6_K.gguf) | Q6_K | 5.0 | very good quality |
74
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.Q8_0.gguf) | Q8_0 | 6.4 | fast, best quality |
75
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-GGUF/resolve/main/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x.f16.gguf) | f16 | 12.0 | 16 bpw, overkill |
76
 
77
  Here is a handy graph by ikawrakow comparing some lower-quality quant
78
  types (lower is better):