Can RX 7900 XT run GLM 5.3 Flash?

Q6 / Q5 / Q4 plus a Q3 estimate

Weights are official GGUF listings when the model page has them. Totals include KV at f16. 1-GPU and 2-GPU columns use the same calculator as this share URL.

System RAM

When the file does not stay in 20 GB VRAM, the spill is system RAM. Shopper lines stay Minimum system RAM needed and RAM needed at full context for UD-Q4_K_XL on this card. Estimate unless a measured R9700 card overlays the kit.

llama.cpp launch

Vulkan first, then ROCm/HIP. Copy a house recipe when one exists. llama.cpp stays first. Strata / vLLM stay on /backends.

# llama.cpp Vulkan. House pin when a recipe exists; otherwise a shape only.
./build-vk/bin/llama-server \
  -m ~/models/UD-Q4_K_XL/GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf \
  -ngl 99 \
  -c 262144 \
  --cache-type-k f16 \
  --cache-type-v f16 \
  --host 127.0.0.1 --port 8080

# HIP shape only — house 35B cards are Vulkan. HIP decode is not measured yet.
./build-hip/bin/llama-server \
  -m ~/models/UD-Q4_K_XL/GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf \
  -ngl 99 \
  -c 262144 \
  --cache-type-k f16 \
  --cache-type-v f16 \
  --host 127.0.0.1 --port 8080

Same model, other cards

GLM 5.3 Flash on the other published Radeon sheets.

• GLM 5.3 Flash on R9700
• GLM 5.3 Flash on PRO W7900
• GLM 5.3 Flash on PRO W7800
• GLM 5.3 Flash on PRO W7700
• GLM 5.3 Flash on PRO W6800
• GLM 5.3 Flash on RX 7900 XTX
• GLM 5.3 Flash on RX 9070 XT
• GLM 5.3 Flash on RX 9070
• GLM 5.3 Flash on RX 9070 GRE
• GLM 5.3 Flash on RX 9060 XT
• GLM 5.3 Flash on RX 7900 GRE
• GLM 5.3 Flash on RX 7800 XT
• GLM 5.3 Flash on RX 7700 XT
• GLM 5.3 Flash on RX 7600 XT
• GLM 5.3 Flash on RX 7600
• GLM 5.3 Flash on RX 6800 XT
• GLM 5.3 Flash on RX 6950 XT
• GLM 5.3 Flash on RX 6700 XT
• GLM 5.3 Flash on Strix Halo

Other models on RX 7900 XT

• Qwen3.6-35B
• Qwen 3.8 Flash
• gpt-oss 20B
• Gemma 3 27B
• Llama 3.3 70B
• Qwen3.6 27B
• Qwen3.8 27B

Check price

Existing /go/ routes for this GPU sheet. Buttons say Check price — we do not print a figure.

FAQ

Can RX 7900 XT run GLM 5.3 Flash?

Fits with RAM offload on the calculator at the shopper UD-Q4_K_XL file and 256K. Q6 / Q5 / Q4 are listed. UD-Q3_K_XL is a labeled estimate. llama.cpp first.

This pair · RX 7900 XT · GLM 5.3 Flash · Calculator · Full requirements at 256K

Which quant should I download?

Prefer the shopper UD-Q4_K_XL file when it still fits. Q6 / Q5 / Q4 are the listed shopper steps. UD-Q3_K_XL is a labeled estimate — not a house pick. Q1/Q2 stay off.

Quants · Q6 / Q5 / Q4 + Q3 estimate

How fast is it?

Measured decode is only the official local desktop 35B llama.cpp Vulkan sweep on one or two R9700s. Every other model × card stays not measured yet. Record a card with amdai-bench.

Contribute · amdai-bench · Benchmarks

Stack Lab

Measure the pair on your box. Doctor and planner are allowlisted. House daily / Flash profiles appear only for those house models.