Written by Jakub Rusinowski · Last updated June 26, 2026
Yes, but it is tight
Yes, but it is tight — GLM-6 9B at Q8_0 needs about 11.6 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM), leaving only ~0.4 GB before the runtime starts swapping. Expect ~25.1 tok/s (estimated), with room for about 8,192 tokens of context.
Confidence: low · Recommended quantization: Q8_0 · Estimated speed: ~25.1 tok/s
| Usable memory for models | 12 GB |
| Memory bandwidth | 360 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 12 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 20 GB | ✗ No | — | — | 18 GB |
| Q8_0 | 11.6 GB | ✓ Yes | 8K | ~25.1 tok/s | 9.6 GB |
| Q6_K | 9.4 GB | ✓ Yes | 16K | ~31.4 tok/s | 7.4 GB |
| Q5_K_M | 8.4 GB | ✓ Yes | 16K | ~35.6 tok/s | 6.4 GB |
| Q4_K_M | 7.4 GB | ✓ Yes | 32K | ~40.6 tok/s | 5.4 GB |
| Q3_K_M | 5.8 GB | ✓ Yes | 32K | ~53.5 tok/s | 3.8 GB |
| Q2_K | 5 GB | ✓ Yes | 32K | ~64.8 tok/s | 3 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| GLM-6 355B-A32B | 219.2 GB | ✗ Too large | — |
| GLM-6 9B | 7.4 GB | ✓ Fits | ~40.6 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, but it is tight — GLM-6 9B at Q8_0 needs about 11.6 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM), leaving only ~0.4 GB before the runtime starts swapping. Expect ~25.1 tok/s (estimated), with room for about 8,192 tokens of context.
Q8_0 — it needs about 11.6 GB of the 12 GB available, downloads as roughly 9.6 GB, and runs at an estimated 25.1 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