Can Granite 4.0 H Small run on the RX 7900 XT?
Yes. At 8K context the best fit is Q3_K_M, using about 15.0 GB of the 19.0 GB usable on the RX 7900 XT. Estimated speed ceiling: ~191 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 11.6 GB Fits | 11.7 GB Fits | 12.1 GB Fits | 13.6 GB Fits | 248 |
| 3-bit (Q3_K_M) • | 15.0 GB Fits | 15.0 GB Fits | 15.4 GB Fits | 16.9 GB Fits | 191 |
| 4-bit (Q4_K_M) • | 18.8 GB Tight | 18.9 GB Tight | 19.2 GB No | 20.7 GB No | 150 |
| 5-bit (Q5_K_M) • | 21.9 GB No | 22.0 GB No | 22.4 GB No | 23.9 GB No | — |
| 6-bit (Q6_K) • | 25.3 GB No | 25.4 GB No | 25.7 GB No | 27.2 GB No | — |
| 8-bit (Q8_0) • | 32.6 GB No | 32.6 GB No | 33.0 GB No | 34.5 GB No | — |
| 16-bit (F16/BF16) • | 60.7 GB No | 60.7 GB No | 61.1 GB No | 62.6 GB No | — |
• real GGUF file size from ibm-granite/granite-4.0-h-small-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Granite 4.0 H Small: RX 7900 XTX (24 GB, launch MSRP $999) at Q4_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the RX 7900 XT: MiniMax H3 Image PE (27B) at Q4_K_M, about 16.8 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
Granite 4.0 H Small on every GPU and Mac · Every model that runs on the RX 7900 XT · Other models that fit 24 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (ibm-granite/granite-4.0-h-small), AMD specs. Model data last checked 2026-11-17; refreshed hourly.