Written by Jakub Rusinowski · Last updated September 11, 2026
Yes, but it is tight
Yes, but it is tight — North Mini Code 1.0 30B-A3B at Q5_K_M needs about 23.8 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~0.2 GB before the runtime starts swapping. Expect ~160.4 tok/s (estimated), with room for about 8,192 tokens of context.
Confidence: low · Recommended quantization: Q5_K_M · Estimated speed: ~160.4 tok/s
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
| Usable memory for models | 24 GB |
| Memory bandwidth | 1008 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 24 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 62.6 GB | ✗ No | — | — | 60 GB |
| Q8_0 | 34.5 GB | ✗ No | — | — | 31.9 GB |
| Q6_K | 27.2 GB | ✗ No | — | — | 24.6 GB |
| Q5_K_M | 23.8 GB | ✓ Yes | 8K | ~160.4 tok/s | 21.3 GB |
| Q4_K_M | 20.7 GB | ✓ Yes | 16K | ~171.9 tok/s | 18.1 GB |
| Q3_K_M | 15.4 GB | ✓ Yes | 32K | ~195.6 tok/s | 12.8 GB |
| Q2_K | 12.4 GB | ✓ Yes | 32K | ~211.6 tok/s | 9.9 GB |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, but it is tight — North Mini Code 1.0 30B-A3B at Q5_K_M needs about 23.8 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~0.2 GB before the runtime starts swapping. Expect ~160.4 tok/s (estimated), with room for about 8,192 tokens of context.
Q5_K_M — it needs about 23.8 GB of the 24 GB available, downloads as roughly 21.3 GB, and runs at an estimated 160.4 tokens/sec with up to 8K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
← Can I Run It? | North Mini Code model page | Check your hardware