Rent a GPU

Can the NVIDIA RTX PRO 6000 Blackwell run GLM-4.7 Flash 30B-A3B?

RTX PRO 6000 Blackwell × GLM-4.7 Flash 30B-A3B8K context
YesRuns fully on the GPU
Memory at FP1663.4 GB of 96 GB
Weights 62.4 GBKV cache 0.4 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~179tokens per second
Max context198Kthe model's full window
  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-4.7 Flash 30B-A3B fully in VRAM at FP16 (full quality), using about 63.4 GB of the 96 GB available, at roughly 179 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts GLM-4.7 Flash 30B-A3B:

ollama run glm-4.7-flash

Ollama's default download is Q4_K_M (about 20 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the RTX PRO 6000 Blackwell

Run it in the cloud

No NVIDIA RTX PRO 6000 Blackwell? Run GLM-4.7 Flash 30B-A3B 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 quality63.4 GBFits~179 tok/s
Q8_0Near-lossless34.2 GBFits~337 tok/s
Q6_KExcellent26.6 GBFits~437 tok/s
Q5_K_MVery good23.2 GBFits~504 tok/s
Q4_K_MGood, most popular20 GBFits~591 tok/s
Q3_K_MNoticeably degraded16.3 GBFits~733 tok/s
Q2_KHeavily degraded12.7 GBFits~956 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-4.7 Flash 30B-A3B 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-4.7 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

Models that run well on the NVIDIA RTX PRO 6000 Blackwell

Frequently asked questions

Can NVIDIA RTX PRO 6000 Blackwell run GLM-4.7 Flash 30B-A3B?

Yes. The NVIDIA RTX PRO 6000 Blackwell can run GLM-4.7 Flash 30B-A3B fully in VRAM at FP16 (full quality), using about 63.4 GB of the 96 GB available, at roughly 179 tokens/second.

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 PRO 6000 Blackwell?

Roughly 179 tokens per second at FP16, estimated from the NVIDIA RTX PRO 6000 Blackwell's 1792 GB/s memory bandwidth.