Rent a GPU

Can the AMD Radeon RX 7900 XTX run GLM-4.7 Flash 30B-A3B?

Radeon RX 7900 XTX × GLM-4.7 Flash 30B-A3B8K context
YesRuns fully on the GPU
Memory at Q5_K_M23.2 GB of 24 GB
Weights 22.2 GBKV cache 0.4 GBRuntime 0.6 GB
QuantQ5_K_MVery good
Speed~270tokens per second
Max context21Ktokens that fit at Q5_K_M
  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 AMD Radeon RX 7900 XTX can run GLM-4.7 Flash 30B-A3B fully in VRAM at Q5_K_M (very good), using about 23.2 GB of the 24 GB available, at roughly 270 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 Q5_K_M, which is very good: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the Radeon RX 7900 XTX

Run it in the cloud

No AMD Radeon RX 7900 XTX? 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 24 GB the AMD Radeon RX 7900 XTX 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 GBFits~270 tok/s
Q4_K_MGood, most popular20 GBFits~317 tok/s
Q3_K_MNoticeably degraded16.3 GBFits~393 tok/s
Q2_KHeavily degraded12.7 GBFits~512 tok/s

Measured speed from real Radeon RX 7900 XTX owners

Tokens per second that people measured on their own AMD Radeon RX 7900 XTX, next to our estimate.

No one has measured GLM-4.7 Flash 30B-A3B on the AMD Radeon RX 7900 XTX yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have a Radeon RX 7900 XTX? 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 AMD Radeon RX 7900 XTX

Frequently asked questions

Can AMD Radeon RX 7900 XTX run GLM-4.7 Flash 30B-A3B?

Yes. The AMD Radeon RX 7900 XTX can run GLM-4.7 Flash 30B-A3B fully in VRAM at Q5_K_M (very good), using about 23.2 GB of the 24 GB available, at roughly 270 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 AMD Radeon RX 7900 XTX?

Roughly 270 tokens per second at Q5_K_M, estimated from the AMD Radeon RX 7900 XTX's 960 GB/s memory bandwidth.