Views
No views yet
Quantized GGUF releases of Atlas-Coder-2-0.5B, optimized for llama.cpp, Ollama, and LM Studio.
| Benchmark | Atlas-Coder-2 | Qwen2.5-Coder-0.5B | DeepSeek-Coder-1.3B | Llama-3.2-1B |
|---|---|---|---|---|
| HumanEval+ | 36.6% 🥇 | 34.1% | 35.4% | 12.2% |
| MBPP+ | 43.9% 🥇 | 42.1% | 39.8% | 25.6% |
Evaluation: EvalPlus (Pass@1, Greedy Decoding)
| File | Quantization | Size | Recommended For |
|---|---|---|---|
| Atlas-Coder-2-0.5B-F16.gguf | F16 | 948 MB | Maximum accuracy & benchmarking |
| Atlas-Coder-2-0.5B-Q8_0.gguf | Q8_0 | 506 MB | Near-lossless inference |
| Atlas-Coder-2-0.5B-Q6_K.gguf | Q6_K | 482 MB | Best quality / size balance |
| Atlas-Coder-2-0.5B-Q5_K_M.gguf | Q5_K_M | 401 MB | Recommended for most users ⭐ |
| Atlas-Coder-2-0.5B-Q4_K_M.gguf | Q4_K_M | 379 MB | Low-memory devices |
1FROM ./Atlas-Coder-2-0.5B-Q5_K_M.gguf
2
3SYSTEM "You are Atlas-Coder, an elite AI coding assistant. You write clean, efficient, and well-documented Python code."
4
5PARAMETER temperature 0.2
6PARAMETER top_p 0.95
7PARAMETER repeat_penalty 1.1
8
9PARAMETER stop "<|im_start|>"
10PARAMETER stop "<|im_end|>"ollama create atlas-coder-2 -f Modelfileollama run atlas-coder-2 "Write a Python function to check whether a string is a palindrome."1./llama-cli \
2 -m Atlas-Coder-2-0.5B-Q5_K_M.gguf \
3 -p "<|im_start|>system\nYou are a helpful coding assistant.<|im_end|>\n<|im_start|>user\nWrite a Python binary search implementation.<|im_end|>\n<|im_start|>assistant\n" \
4 -n 512 \
5 --temp 0.2 \
6 --top-p 0.95 \
7 --repeat-penalty 1.11<|im_start|>system
2{system_message}
3<|im_end|>
4
5<|im_start|>user
6{user_message}
7<|im_end|>
8
9<|im_start|>assistant