mstoeck3/ollama-utils
SHA256
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

todo list

Browse Source
This commit is contained in:
Mario Stöckl
2026-01-18 22:28:43 +01:00
parent 7c89b12c3b
commit fa2c918ac7
1 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@@ -2,6 +2,18 @@
Utilities for managing Ollama LLM models, including automated installation from HuggingFace.
## TODO
| **Use Case** | **Best Model** | **VRAM** | **Speed** | **Why** |
|--------------|----------------|----------|-----------|---------|
| **IDE Autocomplete** | Qwen2.5-Coder-1.5B (Q8) | 2.5GB | 120-150 t/s | Latency critical, FIM optimized |
| **Quick Drafting** | Yi-Coder-9B (Q5_K_M) | 7-8GB | 50-80 t/s | Best speed/quality balance |
| **Large Code Analysis** | Qwen2.5-Coder-14B (Q4_K_M) | 14-16GB | 30-40 t/s | SOTA repo-level, 128K context |
| **Reverse Engineering** | DeepCoder-14B (Q5_K_M) | 11-12GB | 30-50 t/s | Strongest reasoning, RL-trained |
gemma3-12b-it-qat
gemma3-4b-it-qat
## Web Interface
Start the web interface: