Written by Jakub Rusinowski · Last updated August 15, 2026
Yes, comfortably — you'll have ~28.7 GB of headroom running Granite 4.0 Small-H 32B-A9B at Q4_K_M (19.32 GB, ~98 tok/s (est.)) with room for up to 64K context.
| VRAM | 48 GB |
| Memory Bandwidth | 864 GB/s |
| Quant | VRAM needed | Fits 48 GB? | Max context |
|---|---|---|---|
| F16 | 65.7 GB | ✗ No | — |
| Q8_0 | 35.7 GB | ✓ Yes | 32K |
| Q6_K | 28 GB | ✓ Yes | 64K |
| Q5_K_M | 24.4 GB | ✓ Yes | 64K |
| Q4_K_M | 21 GB | ✓ Yes | 64K |
| Q3_K_M | 15.4 GB | ✓ Yes | 128K |
| Q2_K | 12.2 GB | ✓ Yes | 128K |
VRAM needed assumes a 4K-token context with an f16 KV cache; “Max context” is the largest window that still fits in 48 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
| Granite 4.0 Small-H 32B-A9B | Q4_K_M · 19.32 GB · ~98 tok/s (est.) |
At 2 hrs/day, buying (~$7,499) beats renting at $0.34/hr after about 30.6 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Yes, comfortably — you'll have ~28.7 GB of headroom running Granite 4.0 Small-H 32B-A9B at Q4_K_M (19.32 GB, ~98 tok/s (est.)) with room for up to 64K context.
Granite 4.0 Small-H 32B-A9B at Q4_K_M quantization (19.32 GB), estimated ~98 tokens/sec, up to 64K context.
← Can I Run It? | IBM Granite 4.0 Model Page | NVIDIA L40S GPU Page | Check Your Hardware