Architecture truth card — GLM-5.2
← Open the interactive VRAM & cost calculator on the homepage
Exact VRAM matrix — 3 precisions × 3 context lengths
| Precision | 8192 tokens ctx | 32768 tokens ctx | 131072 tokens ctx |
|---|---|---|---|
| FP16/BF16 16-bit | 1403.19 / 0.69 / 71.66 Total 1475.53 GiB | 1403.19 / 2.74 / 71.66 Total 1477.59 GiB | 1403.19 / 10.97 / 71.66 Total 1485.81 GiB |
| FP8/INT8 8-bit | 701.59 / 0.69 / 36.58 Total 738.86 GiB | 701.59 / 2.74 / 36.58 Total 740.92 GiB | 701.59 / 10.97 / 36.58 Total 749.14 GiB |
| INT4/AWQ 4.5-bit | 394.65 / 0.69 / 21.23 Total 416.56 GiB | 394.65 / 2.74 / 21.23 Total 418.62 GiB | 394.65 / 10.97 / 21.23 Total 426.85 GiB |
Each cell: Weights GiB / GQA KV Cache GiB / Runtime Overhead GiB; bold line = Total VRAM GiB. Concurrency = 1, FP16 KV cache (2 bytes), overhead = 1.5 + 0.05 × weights GiB.
Terminal speed-math — no install needed
Re-run this exact sizing from your own terminal:
curl -fsSL https://gpuvram.pages.dev/vram-cli.py | python3 - glm-5-2 --ctx 32768
Live cheapest GPU configurations
| Scenario | Cheapest fitting rig (top 3) | Total VRAM | Lowest $/hr | 730 h/mo | Deploy |
|---|---|---|---|---|---|
| INT4 @ 32K ctx | 4x H200 NVL 143GB | 572 GiB | $2.00 | $1460.00 | Deploy on RunPodCheck Vast.ai Verified |
| INT4 @ 32K ctx | 4x MI300X 192GB | 768 GiB | $2.00 | $1460.00 | Deploy on RunPodCheck Vast.ai Verified |
| INT4 @ 32K ctx | 8x H200 NVL 143GB | 1144 GiB | $4.00 | $2920.00 | Deploy on RunPodCheck Vast.ai Verified |
| FP8 @ 32K ctx | 4x MI300X 192GB | 768 GiB | $2.00 | $1460.00 | Deploy on RunPodCheck Vast.ai Verified |
| FP8 @ 32K ctx | 8x H200 NVL 143GB | 1144 GiB | $4.00 | $2920.00 | Deploy on RunPodCheck Vast.ai Verified |
| FP8 @ 32K ctx | 8x MI300X 192GB | 1536 GiB | $4.00 | $2920.00 | Deploy on RunPodCheck Vast.ai Verified |
| FP16 @ 32K ctx | 8x MI300X 192GB | 1536 GiB | $4.00 | $2920.00 | Deploy on RunPodCheck Vast.ai Verified |
| FP16 @ 32K ctx | 8x B300 288GB | 2304 GiB | $55.52 | $40529.60 | Deploy on RunPodCheck Vast.ai Verified |
What over-provisioning costs you
Running GLM-5.2 production traffic at INT4 / 32K context on the cheapest fitting rig (4x H200 NVL 143GB) bills $1460.00 per month (730 h). Defaulting to full FP16 forces a larger rig — 8x MI300X 192GB at $2920.00/mo. Paying $2920.00 instead of $1460.00 every single month is the price of skipping 4-bit AWQ quantization; if your quality budget allows INT4, that gap is pure waste.