StarCoder2 15B vs Qwen 2.5 Coder 14B
Comparing VRAM requirements, performance, and capabilities for running these models locally with Ollama.
Parameters
15B
Context
16K
VRAM Range
10.5–17 GB
Recommended
Q8_0 (17 GB)
ByBigCode·LicenseBigCode Open RAIL-M v1
Parameters
14B
Context
128K
VRAM Range
12–33 GB
Recommended
Q4_K_M (12 GB)
ByAlibaba·LicenseApache 2.0
VRAM Requirements by Quantization
Side-by-side memory needs at each quality level.
| Quantization | StarCoder2 15B | Qwen 2.5 Coder 14B | Difference |
|---|---|---|---|
| Q4_K_M | 10.5 GB | 12 GB | -1.5 GB |
| Q8_0 | 17 GB | 19 GB | -2.0 GB |
| F16 | — | 33 GB | — |
Capabilities
Feature support comparison.
| Capability | StarCoder2 15B | Qwen 2.5 Coder 14B |
|---|---|---|
| text generation | Yes | Yes |
| code generation | Yes | Yes |
Benchmark Scores
Higher is better. Scores from published evaluations.
| Benchmark | StarCoder2 15B | Qwen 2.5 Coder 14B |
|---|---|---|
| mmlu | 54.0 | 72.0 |
Hardware Compatibility
Can each model run at recommended quantization on common VRAM tiers?
| VRAM | StarCoder2 15B | Qwen 2.5 Coder 14B |
|---|---|---|
| 8 GB | No | Offload |
| 12 GB | Offload | Offload |
| 16 GB | Offload | Runs |
| 24 GB | Runs | Runs |
| 32 GB | Runs | Runs |
| 48 GB | Runs | Runs |
| 64 GB | Runs | Runs |
| 96 GB | Runs | Runs |
Run StarCoder2 15B
ollama run starcoder2:15b-q8_0Run Qwen 2.5 Coder 14B
ollama run qwen2.5-coder:14b-instruct-q4_K_MCheck your exact hardware
Use the compatibility checker to see how each model performs on your specific GPU or Mac.