Can Titan X Pascal 12GB run GLM-5.2?

NVIDIA · 12 GB GDDR5X · 480 GB/s bandwidth · Z.ai · 753.3B (active 40B) · MoE · model ctx up to 1000K

CUDA

No — GLM-5.2 at Q4 needs ≈ 419.31 GB even at 4K context, beyond the Titan X Pascal 12GB's 12 GB GDDR5X. It would only run with heavy CPU/disk offload. FP16 needs ≈ 1515.6 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	419.31 GB	No	—
Q4	8K default	423.31 GB	No	—
Q4	32K	447.31 GB	No	—
FP16	4K	1511.6 GB	No	—
FP16	8K default	1515.6 GB	No	—
FP16	32K	1539.6 GB	No	—

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

Quant	Weights	KV cache	Overhead	Total needed	Titan X Pascal 12GB VRAM
Q4	414.31 GB	8.0 GB	1 GB	423.31 GB	12 GB
FP16	1506.6 GB	8.0 GB	1 GB	1515.6 GB	12 GB

Other GPUs that run GLM-5.2

• DGX Spark (GH200 480GB) — ≈8.0 tok/s Q4 est.

All GPUs for GLM-5.2 →

Other models for the Titan X Pascal 12GB

• MiniCPM5-1B — ≈282.8 tok/s Q4 est.
• Qwen3.5-2B — ≈152.7 tok/s Q4 est.
• DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx — ≈132.8 tok/s Q4 est.
• Llama-3.2-3B-Instruct — ≈95.5 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈76.4 tok/s Q4 est.
• NVIDIA-Nemotron-3-Nano-4B-BF16 — ≈76.4 tok/s Q4 est.
• Qwen3-4B-Thinking-2507 — ≈76.4 tok/s Q4 est.
• gemma-4-E2B-it — ≈59.9 tok/s Q4 est.

All models on the Titan X Pascal 12GB →