Written by Jakub Rusinowski · Last updated April 28, 2025
Yes — comfortably
Yes, comfortably — Qwen 3 14B at Q6_K needs about 14.3 GB of the 19.2 GB usable on 24 GB system RAM, leaving ~4.9 GB spare and running at ~5.2 tok/s (estimated), with room for about 32,768 tokens of context.
Confidence: high · Recommended quantization: Q6_K · Estimated speed: ~5.2 tok/s
| Usable memory for models | 19.2 GB |
| Memory bandwidth | 90 GB/s |
| Quant | Memory needed | Fits 19.2 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 31.7 GB | ✗ No | — | — | 29.6 GB |
| Q8_0 | 17.9 GB | ✓ Yes | 8K | ~4.1 tok/s | 15.7 GB |
| Q6_K | 14.3 GB | ✓ Yes | 32K | ~5.2 tok/s | 12.1 GB |
| Q5_K_M | 12.6 GB | ✓ Yes | 32K | ~5.9 tok/s | 10.5 GB |
| Q4_K_M | 11.1 GB | ✓ Yes | 32K | ~6.9 tok/s | 8.9 GB |
| Q3_K_M | 8.5 GB | ✓ Yes | 64K | ~9.4 tok/s | 6.3 GB |
| Q2_K | 7 GB | ✓ Yes | 64K | ~11.8 tok/s | 4.9 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Qwen 3 235B-A22B (MoE) | 144.3 GB | ✗ Too large | — |
| Qwen 3 32B | 22.8 GB | ✗ Too large | — |
| Qwen 3 30B-A3B (MoE) | 20 GB | ✗ Too large | — |
| Qwen 3 14B | 11.1 GB | ✓ Fits | ~6.9 tok/s |
| Qwen 3 8B | 7 GB | ✓ Fits | ~11.8 tok/s |
llama.cpp (CPU build) or Ollama — both run without a GPU
Yes, comfortably — Qwen 3 14B at Q6_K needs about 14.3 GB of the 19.2 GB usable on 24 GB system RAM, leaving ~4.9 GB spare and running at ~5.2 tok/s (estimated), with room for about 32,768 tokens of context.
Q6_K — it needs about 14.3 GB of the 19.2 GB available, downloads as roughly 12.1 GB, and runs at an estimated 5.2 tokens/sec with up to 32K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
llama.cpp (CPU build) or Ollama — both run without a GPU