Update README.md
Browse files
README.md
CHANGED
@@ -77,6 +77,32 @@ For simpler coding problems, lower quants will work well; but for complex/multi-
|
|
77 |
|
78 |
---
|
79 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
# Devstral Small 1.0
|
81 |
|
82 |
Devstral is an agentic LLM for software engineering tasks built under a collaboration between [Mistral AI](https://mistral.ai/) and [All Hands AI](https://www.all-hands.dev/) 🙌. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench which positionates it as the #1 open source model on this [benchmark](#benchmark-results).
|
|
|
77 |
|
78 |
---
|
79 |
|
80 |
+
<B>QUANTS:</b>
|
81 |
+
|
82 |
+
---
|
83 |
+
|
84 |
+
Special Thanks to Team Mradermacher and Team Nightmedia for the quants:
|
85 |
+
|
86 |
+
GGUF:
|
87 |
+
|
88 |
+
https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-GGUF
|
89 |
+
|
90 |
+
GGUF-IMATRIX:
|
91 |
+
|
92 |
+
https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF
|
93 |
+
|
94 |
+
MLX:
|
95 |
+
|
96 |
+
https://huggingface.co/nightmedia/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-q6-mlx
|
97 |
+
|
98 |
+
https://huggingface.co/nightmedia/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-q8-mlx
|
99 |
+
|
100 |
+
https://huggingface.co/nightmedia/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-q5-mlx
|
101 |
+
|
102 |
+
https://huggingface.co/nightmedia/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-q4-mlx
|
103 |
+
|
104 |
+
---
|
105 |
+
|
106 |
# Devstral Small 1.0
|
107 |
|
108 |
Devstral is an agentic LLM for software engineering tasks built under a collaboration between [Mistral AI](https://mistral.ai/) and [All Hands AI](https://www.all-hands.dev/) 🙌. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench which positionates it as the #1 open source model on this [benchmark](#benchmark-results).
|