← Can It Run? — GPU compatibility matrix · Local LLMs guide
Qwen 2.5 14B needs 8.5 GB VRAM at Q4. The RTX 3080 10GB has 10 GB.
🌐 Qwen 2.5 14B (Alibaba) is a 14B-parameter model for code, math, multilingual reasoning. Excellent for technical tasks and code generation. The question is whether the RTX 3080 10GB’s 10 GB of VRAM can hold it — here’s the exact math.
VRAM requirements
| Quantization | VRAM needed | RTX 3080 10GB |
|---|---|---|
| Q4_K_M (recommended) | 8.5 GB | ✅ |
| Q8_0 (near-lossless) | 14.5 GB | ❌ |
Expected performance
Running Qwen 2.5 14B at Q4 on the RTX 3080 10GB, expect roughly ~35 tokens/sec in Ollama or llama.cpp — comfortably faster than reading speed, so chat feels responsive.
Headroom: 8.5 GB used of 10 GB leaves about 1.5 GB free for KV cache (context). That’s fine for 4-8K context; for 32K+ you may need a smaller batch or a lower quant.
About the RTX 3080 10GB
Architecture: Ampere · VRAM: 10 GB · Price: ~$400 used.
Good: Fast memory bandwidth, strong tokens/sec for its tier
Watch out: Only 10GB — awkward middle ground, limits model size
Check current RTX 3080 10GB price on Amazon →
Related checks
Other models on the RTX 3080 10GB
🎯 LLM Hardware Checker
Enter your exact GPU + RAM, see every model you can run.
💾 VRAM Requirements
Exact VRAM per model at Q4/Q5/Q8/FP16 with context scaling.
Frequently asked questions
Can the RTX 3080 10GB run Qwen 2.5 14B?
Yes — runs great at Q4 (recommended). Qwen 2.5 14B needs 8.5 GB VRAM at Q4_K_M; the RTX 3080 10GB has 10 GB.
How much VRAM does Qwen 2.5 14B need?
Qwen 2.5 14B needs about 8.5 GB at Q4_K_M (recommended) and 14.5 GB at Q8_0.
How many tokens per second will the RTX 3080 10GB get on Qwen 2.5 14B?
Roughly ~35 tokens/sec at Q4 in Ollama or llama.cpp.