Rent a GPU

Can the NVIDIA RTX 5080 run GLM-5.3 Flash 320B-A18B?

RTX 5080 × GLM-5.3 Flash 320B-A18B8K context
NoDoes not fit in memory
Memory at Q4_K_M195.3 GB of 16 GB
Weights 194.6 GBKV cache 0.1 GBRuntime 0.6 GB
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

No. Even at Q4_K_M, GLM-5.3 Flash 320B-A18B needs about 195.3 GB, but the NVIDIA RTX 5080 has 16 GB usable. You could offload some layers to system RAM, but it will be very slow.

Try other context lengths

Run it in the cloud

Too big for the NVIDIA RTX 5080? Run GLM-5.3 Flash 320B-A18B on a rented GPU instead.

Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 16 GB the NVIDIA RTX 5080 can use.

QuantQualityMemoryFits?Speed
FP16Full quality642.7 GBToo big—
Q8_0Near-lossless341.8 GBToo big—
Q6_KExcellent263.9 GBToo big—
Q5_K_MVery good229 GBToo big—
Q4_K_MGood, most popular195.3 GBToo big—
Q3_K_MNoticeably degraded157.6 GBToo big—
Q2_KHeavily degraded121.1 GBToo big—

Measured speed from real RTX 5080 owners

Tokens per second that people measured on their own NVIDIA RTX 5080, next to our estimate.

No one has measured GLM-5.3 Flash 320B-A18B on the NVIDIA RTX 5080 yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 5080? Add your real speed

One command times GLM-5.3 Flash 320B-A18B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh

Windows (PowerShell)

irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

Models that run well on the NVIDIA RTX 5080

Frequently asked questions

Can NVIDIA RTX 5080 run GLM-5.3 Flash 320B-A18B?

No. Even at Q4_K_M, GLM-5.3 Flash 320B-A18B needs about 195.3 GB, but the NVIDIA RTX 5080 has 16 GB usable. You could offload some layers to system RAM, but it will be very slow.

How much VRAM does GLM-5.3 Flash 320B-A18B need?

About 195.3 GB at Q4_K_M with 8,192 tokens of context, and about 642.7 GB at full FP16 precision.

How fast is GLM-5.3 Flash 320B-A18B on the NVIDIA RTX 5080?

It does not fit in the NVIDIA RTX 5080's memory, so most layers would run from system RAM and generation would be very slow.