Written by Jakub Rusinowski · Last updated June 26, 2026
Yes — comfortably
Yes, comfortably — GLM-6 9B at Q8_0 needs about 11.6 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving ~20.4 GB spare and running at ~101.9 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~101.9 tok/s
| Usable memory for models | 32 GB |
| Memory bandwidth | 1792 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 20 GB | ✓ Yes | 64K | ~62.2 tok/s | 18 GB |
| Q8_0 | 11.6 GB | ✓ Yes | 64K | ~101.9 tok/s | 9.6 GB |
| Q6_K | 9.4 GB | ✓ Yes | 64K | ~122.2 tok/s | 7.4 GB |
| Q5_K_M | 8.4 GB | ✓ Yes | 64K | ~134.4 tok/s | 6.4 GB |
| Q4_K_M | 7.4 GB | ✓ Yes | 64K | ~148.4 tok/s | 5.4 GB |
| Q3_K_M | 5.8 GB | ✓ Yes | 64K | ~180.2 tok/s | 3.8 GB |
| Q2_K | 5 GB | ✓ Yes | 64K | ~204.2 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 | ~148.4 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, comfortably — GLM-6 9B at Q8_0 needs about 11.6 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving ~20.4 GB spare and running at ~101.9 tok/s (estimated), with room for about 65,536 tokens of context.
Q8_0 — it needs about 11.6 GB of the 32 GB available, downloads as roughly 9.6 GB, and runs at an estimated 101.9 tokens/sec with up to 64K 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