Rent a GPU

Can the NVIDIA RTX 5060 Ti 16GB run GLM-4.7 Flash 30B-A3B?

RTX 5060 Ti 16GB × GLM-4.7 Flash 30B-A3B8K context
Yes, with heavy quantizationFits only at a low-quality quant
Memory at Q2_K12.7 GB of 16 GB
Weights 11.7 GBKV cache 0.4 GBRuntime 0.6 GB
QuantQ2_KHeavily degraded
Speed~239tokens per second
Max context66Ktokens that fit at Q2_K
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Only just. GLM-4.7 Flash 30B-A3B fits on the NVIDIA RTX 5060 Ti 16GB at Q2_K, which costs noticeable quality. Expect about 239 tokens/second. A card with more memory is a better experience.

Try other context lengths

Run it with Ollama

Ollama's default glm-4.7-flash download is Q4_K_M, which needs about 20 GB, more than the 16 GB available. Download the Q2_K GGUF instead (LM Studio lists quants per model), or try a smaller context length.

New to this? Step-by-step setup for the RTX 5060 Ti 16GB

Run it in the cloud

Want full quality? Run GLM-4.7 Flash 30B-A3B on a bigger rented GPU.

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 5060 Ti 16GB can use.

QuantQualityMemoryFits?Speed
FP16Full quality63.4 GBToo big—
Q8_0Near-lossless34.2 GBToo big—
Q6_KExcellent26.6 GBToo big—
Q5_K_MVery good23.2 GBToo big—
Q4_K_MGood, most popular20 GBToo big—
Q3_K_MNoticeably degraded16.3 GBToo big—
Q2_KHeavily degraded12.7 GBFits~239 tok/s

Measured speed from real RTX 5060 Ti 16GB owners

Tokens per second that people measured on their own NVIDIA RTX 5060 Ti 16GB, next to our estimate.

No one has measured GLM-4.7 Flash 30B-A3B on the NVIDIA RTX 5060 Ti 16GB yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 5060 Ti 16GB? Add your real speed

One command times GLM-4.7 Flash 30B-A3B 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 -s -- glm-4.7-flash

Windows (PowerShell)

$env:GPUFIT_MODEL="glm-4.7-flash"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run GLM-4.7 Flash 30B-A3B comfortably

Check Radeon RX 7900 XT prices

Models that run well on the NVIDIA RTX 5060 Ti 16GB

Frequently asked questions

Can NVIDIA RTX 5060 Ti 16GB run GLM-4.7 Flash 30B-A3B?

Only just. GLM-4.7 Flash 30B-A3B fits on the NVIDIA RTX 5060 Ti 16GB at Q2_K, which costs noticeable quality. Expect about 239 tokens/second. A card with more memory is a better experience.

How much VRAM does GLM-4.7 Flash 30B-A3B need?

About 20 GB at Q4_K_M with 8,192 tokens of context, and about 63.4 GB at full FP16 precision.

How fast is GLM-4.7 Flash 30B-A3B on the NVIDIA RTX 5060 Ti 16GB?

Roughly 239 tokens per second at Q2_K, estimated from the NVIDIA RTX 5060 Ti 16GB's 448 GB/s memory bandwidth.