Rent a GPU

Can the NVIDIA RTX PRO 6000 Blackwell run GLM-4.5-Air 106B-A12B?

RTX PRO 6000 Blackwell × GLM-4.5-Air 106B-A12B8K context
YesRuns fully on the GPU
Memory at Q6_K89.1 GB of 96 GB
Weights 86.9 GBKV cache 1.5 GBRuntime 0.6 GB
QuantQ6_KExcellent
Speed~109tokens per second
Max context43Ktokens that fit at Q6_K
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX PRO 6000 Blackwell can run GLM-4.5-Air 106B-A12B fully in VRAM at Q6_K (excellent), using about 89.1 GB of the 96 GB available, at roughly 109 tokens/second.

Try other context lengths

Run it in the cloud

No NVIDIA RTX PRO 6000 Blackwell? Run GLM-4.5-Air 106B-A12B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

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 96 GB the NVIDIA RTX PRO 6000 Blackwell can use.

QuantQualityMemoryFits?Speed
FP16Full quality214.1 GBToo big—
Q8_0Near-lossless114.8 GBToo big—
Q6_KExcellent89.1 GBFits~109 tok/s
Q5_K_MVery good77.5 GBFits~126 tok/s
Q4_K_MGood, most popular66.4 GBFits~148 tok/s
Q3_K_MNoticeably degraded54 GBFits~183 tok/s
Q2_KHeavily degraded41.9 GBFits~239 tok/s

Measured speed from real RTX PRO 6000 Blackwell owners

Tokens per second that people measured on their own NVIDIA RTX PRO 6000 Blackwell, next to our estimate.

No one has measured GLM-4.5-Air 106B-A12B on the NVIDIA RTX PRO 6000 Blackwell yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX PRO 6000 Blackwell? Add your real speed

One command times GLM-4.5-Air 106B-A12B 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

GPUs that run GLM-4.5-Air 106B-A12B comfortably

Models that run well on the NVIDIA RTX PRO 6000 Blackwell

Frequently asked questions

Can NVIDIA RTX PRO 6000 Blackwell run GLM-4.5-Air 106B-A12B?

Yes. The NVIDIA RTX PRO 6000 Blackwell can run GLM-4.5-Air 106B-A12B fully in VRAM at Q6_K (excellent), using about 89.1 GB of the 96 GB available, at roughly 109 tokens/second.

How much VRAM does GLM-4.5-Air 106B-A12B need?

About 66.4 GB at Q4_K_M with 8,192 tokens of context, and about 214.1 GB at full FP16 precision.

How fast is GLM-4.5-Air 106B-A12B on the NVIDIA RTX PRO 6000 Blackwell?

Roughly 109 tokens per second at Q6_K, estimated from the NVIDIA RTX PRO 6000 Blackwell's 1792 GB/s memory bandwidth.