Can I Run GLM-5 / GLM-5.1 on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?
作者： Jakub Rusinowski · 最后更新： 2026年5月1日
No
No — GLM-5 / GLM-5.1 does not fit in RTX 3090 Desktop (24 GB VRAM, 64 GB RAM). Even at Q2_K it needs about 250.6 GB against 24 GB usable, a shortfall of roughly 226.6 GB.
Confidence: medium
Get a personalized upgrade path →
RTX 3090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model
| Usable memory for models | 24 GB |
| Memory bandwidth | 936 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
GLM-5 / GLM-5.1 on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization
| Quant | Memory needed | Fits 24 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 1494 GB | ✗ No | — | — | 1488 GB |
| Q8_0 | 796.5 GB | ✗ No | — | — | 790.5 GB |
| Q6_K | 616.1 GB | ✗ No | — | — | 610.1 GB |
| Q5_K_M | 533.3 GB | ✗ No | — | — | 527.3 GB |
| Q4_K_M | 455.2 GB | ✗ No | — | — | 449.2 GB |
| Q3_K_M | 323.2 GB | ✗ No | — | — | 317.1 GB |
| Q2_K | 250.6 GB | ✗ No | — | — | 244.6 GB |
What to watch out for
- This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
RTX 3090 desktop limitations
- The cheapest route to 24 GB of VRAM, and the standard used-market recommendation for local LLMs.
- Older architecture: no FP8 acceleration, and higher idle power than a current card.
Recommended setup
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 24 GB of VRAM on the NVIDIA GeForce RTX 3090 at 936 GB/s.
- 64 GB of system RAM available for CPU offload when a model exceeds VRAM.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is inferred from the parameter count because this model does not publish its full attention configuration.
FAQ
Can I run GLM-5 / GLM-5.1 on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?
No — GLM-5 / GLM-5.1 does not fit in RTX 3090 Desktop (24 GB VRAM, 64 GB RAM). Even at Q2_K it needs about 250.6 GB against 24 GB usable, a shortfall of roughly 226.6 GB.
What limits GLM-5 / GLM-5.1 on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?
Memory. RTX 3090 Desktop (24 GB VRAM, 64 GB RAM) provides about 24 GB usable, and the smallest quantization of this model needs 250.6 GB.
Which runtime should I use?
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Other Computers
Other Models on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
- GPT-OSS on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
- Granite 3.0 on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
- IBM Granite 4.0 on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
- IBM Granite 4.1 on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
- IBM Granite 4.2 on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)
GLM-5 / GLM-5.1 on GPUs
- GLM-5 / GLM-5.1 on NVIDIA GeForce RTX 5090
- GLM-5 / GLM-5.1 on NVIDIA GeForce RTX 5070
- GLM-5 / GLM-5.1 on NVIDIA GeForce RTX 5060 Ti 8GB
- GLM-5 / GLM-5.1 on NVIDIA GeForce RTX 5060
What This Model Is Good At
- Best local LLMs for coding
- Best local LLMs for document analysis
- Best local LLMs for enterprise assistant
Model & Tools
← Can I Run It? | GLM-5 / GLM-5.1 model page | Check your hardware