Can I Run GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 5090?
作者： Jakub Rusinowski · 最后更新： 2026年8月15日
Yes, comfortably — you'll have ~12.7 GB of headroom running GLM-Z1 32B (Reasoning) at Q4_K_M (19.3 GB, ~64 tok/s (est.)) with room for up to 32K context.
See what else this hardware can run →
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
NVIDIA GeForce RTX 5090 Specs
| VRAM | 32 GB |
| Memory Bandwidth | 1792 GB/s |
GLM-Z1 32B (Reasoning) on the NVIDIA GeForce RTX 5090: VRAM by quantization
| Quant | VRAM needed | Fits 32 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 65.7 GB | ✗ No | — | — |
| Q8_0 | 35.7 GB | ✗ No | — | Build for this |
| Q6_K | 28 GB | ✓ Yes | 16K | — |
| Q5_K_M | 24.4 GB | ✓ Yes | 32K | — |
| Q4_K_M | 21 GB | ✓ Yes | 32K | Build for this |
| Q3_K_M | 15.4 GB | ✓ Yes | 64K | — |
| Q2_K | 12.2 GB | ✓ Yes | 64K | — |
Assumes a 4K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 32 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA GeForce RTX 5090: 8K 22 GB · 32K 27.5 GB · 125K 49 GB ✗. Past 125K it no longer fits 32 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? GLM-Z1 32B (Reasoning) on 32 GB of system RAM, CPU only: runs comfortably.
GLM-4.7 / GLM-Z1 Sizes That Fit the NVIDIA GeForce RTX 5090
| GLM-Z1 32B (Reasoning) | Q4_K_M · 19.3 GB · ~64 tok/s (est.) |
| GLM-4.7-Flash 30B-A3B | Q4_K_M · 18.1 GB · ~249 tok/s (est.) |
| GLM-4 9B | Q4_K_M · 5.4 GB · ~161 tok/s (est.) |
At 2 hrs/day, buying (~$1,999) beats renting at $0.34/hr after about 8.2 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Is the NVIDIA GeForce RTX 5090 enough to run GLM-4.7 / GLM-Z1 locally?
Yes, comfortably — you'll have ~12.7 GB of headroom running GLM-Z1 32B (Reasoning) at Q4_K_M (19.3 GB, ~64 tok/s (est.)) with room for up to 32K context.
What's the best GLM-4.7 / GLM-Z1 size for the NVIDIA GeForce RTX 5090?
GLM-Z1 32B (Reasoning) at Q4_K_M quantization (19.3 GB), estimated ~64 tokens/sec, up to 32K context.
Every GLM-4.7 / GLM-Z1 size on the NVIDIA GeForce RTX 5090
| Size | VRAM | Verdict | Speed |
|---|---|---|---|
| GLM-Z1 32B (Reasoning) | 19.3 GB | Runs | ~64 tok/s |
| GLM-4.7-Flash 30B-A3B | 18.1 GB | Runs | ~249 tok/s |
| GLM-4 9B | 5.4 GB | Runs | ~161 tok/s |
GLM-4.7 / GLM-Z1 on Other GPUs
- GLM-4.7 / GLM-Z1 on Apple M4
- GLM-4.7 / GLM-Z1 on Apple M2 Pro
- GLM-4.7 / GLM-Z1 on Apple M1 Pro
- GLM-4.7 / GLM-Z1 on Apple M5
- GLM-4.7 / GLM-Z1 on Apple M3 Pro
Popular Models on the NVIDIA GeForce RTX 5090
- DeepSeek R1 on NVIDIA GeForce RTX 5090
- Qwen 3 on NVIDIA GeForce RTX 5090
- Qwen 2.5 Family on NVIDIA GeForce RTX 5090
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | GLM-4.7 / GLM-Z1 Model Page | NVIDIA GeForce RTX 5090 GPU Page | Check Your Hardware