GLM-4.5 vs Qwen3-235B-A22B
GLM-4.5 (358.3B parameters) and Qwen3-235B-A22B (235.1B parameters) side by side: the memory each needs at every precision, what it costs to run on a live GPU, and the context window, KV cache and license where they are published. Numbers are computed from the models' published specs; this page does not rank quality.
Side by side
| Fact | GLM-4.5 | Qwen3-235B-A22B |
|---|---|---|
| Parameters | 358.3B | 235.1B |
| Architecture | Grouped-query attention; mixture of 160 experts, 8 active per token | Grouped-query attention; mixture of 128 experts, 8 active per token |
| Context length | 131,072 tokens | 40,960 tokens |
| License | – | – |
| Published precision | BF16 | BF16 |
| VRAM needed, As published | 801 GB | 525 GB |
| VRAM needed, FP8 | 400 GB | 263 GB |
| VRAM needed, INT4 | 200 GB | 131 GB |
| Cheapest live fit, As published | No live fit | RTX PRO 6000 × 6 · $8.25/hr |
| Cheapest live fit, FP8 | RTX PRO 6000 × 5 · $6.88/hr | RTX PRO 6000 × 3 · $4.13/hr |
| Cheapest live fit, INT4 | RTX A6000 × 5 · $1.81/hr | RTX A5000 × 6 · $1.06/hr |
| KV cache per token (16-bit) | 368 KB | 188 KB |
| KV cache at 32k tokens | 11.5 GB | 5.88 GB |
| KV cache at 128k tokens | 46.0 GB | 23.5 GB |
VRAM is the weight size at each precision times a flat 1.2 overhead; see the methodology. The FP8 and INT4 rows need a quantized checkpoint or an engine that quantizes on load. The fit is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does. KV cache is for one sequence at 16-bit, computed from each model's config where the attention layout is known.
Which to pick
- Qwen3-235B-A22B needs less VRAM at its published precision (525 GB against 801 GB), so it fits on a smaller GPU.
- GLM-4.5 lists the longer context window (131,072 tokens against 40,960).
- Qwen3-235B-A22B caches less per sequence at 32k tokens (5.9 GB against 11.5 GB), leaving more memory for batching.
These follow only from the facts in the table above. Whether either model does your task well is a separate question this page does not answer.
Keep reading
- GLM-4.5: full VRAM table and live GPU fit
- Qwen3-235B-A22B: full VRAM table and live GPU fit
- The GLM model series
- The Qwen model series
Other comparisons
