Can 2x RTX Pro 6000 (Blackwell, 96 GB) run GLM-5.3 Flash?

Q: Can 2x RTX Pro 6000 (Blackwell, 96 GB) run GLM-5.3 Flash?

Yes. Measured 238.3 tok/s generation on 2x RTX Pro 6000 (Blackwell, 96 GB), via TensorFold, 1 stream, EXL3 4-bit + DFlash2. Source: https://mia-ai.net/models/GLM-5.3-Flash-EXL3-2x-RTX-PRO-6000-TensorFold At Q4_K_M the weights are about 195.8 GB, more than 192 GB, so Q4_K_M doesn't fully fit without offloading part of the model to system RAM.

Yes. Measured 238.3 tok/s generation (TensorFold, 1 stream, EXL3 4-bit + DFlash2; source).

Every measured result for GLM-5.3 Flash on 2x RTX Pro 6000 (Blackwell, 96 GB)

Build	Quant / setup	Engine	tok/s
2x RTX PRO 6000: GLM-5.3 Flash EXL3 4-bit on TensorFold, 238.3 tok/s (Mia's AI Lab recipe)	EXL3 4-bit + DFlash2	TensorFold, 1 stream	238.3	source

Memory: 2x RTX Pro 6000 (Blackwell, 96 GB) has 192 GB. GLM-5.3 Flash weights are about 195.8 GB at Q4_K_M (320B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator. At Q4_K_M the weights are about 195.8 GB, more than 192 GB, so Q4_K_M doesn't fully fit without offloading part of the model to system RAM.

Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.

All measured speeds for GLM-5.3 Flash: best home rig for GLM-5.3 Flash.

GLM-5.3 Flash on other hardware: 2x DGX Spark (GB10) · 2x RTX Pro 6000 Max-Q (Blackwell, 96 GB, 300 W) · 3x DGX Spark (GB10) · 4x DGX Spark (GB10) · 4x RTX Pro 6000 (Blackwell, 96 GB) · RTX 5090

Not enough VRAM? Rent before you buy. Run GLM-5.3 Flash on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.