Can SenseNova Loop 9B run on the RX 7900 XT?
Yes. At 8K context the best fit is Q8_0, using about 10.0 GB of the 19.0 GB usable on the RX 7900 XT. Estimated speed ceiling: ~84 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) | 4.3 GB Fits | 4.4 GB Fits | 5.2 GB Fits | 8.2 GB Fits | 227 |
| 3-bit (Q3_K_M) • | 5.3 GB Fits | 5.4 GB Fits | 6.2 GB Fits | 9.2 GB Fits | 172 |
| 4-bit (Q4_K_M) • | 6.2 GB Fits | 6.4 GB Fits | 7.1 GB Fits | 10.1 GB Fits | 142 |
| 5-bit (Q5_K_M) | 7.2 GB Fits | 7.4 GB Fits | 8.1 GB Fits | 11.1 GB Fits | 119 |
| 6-bit (Q6_K) | 8.2 GB Fits | 8.3 GB Fits | 9.1 GB Fits | 12.1 GB Fits | 104 |
| 8-bit (Q8_0) • | 9.9 GB Fits | 10.0 GB Fits | 10.8 GB Fits | 13.8 GB Fits | 84 |
| 16-bit (F16/BF16) | 18.5 GB Tight | 18.7 GB Tight | 19.4 GB No | 22.4 GB No | 42 |
• real GGUF file size from guideboardlabs/SenseNova-Loop-9B-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs SenseNova Loop 9B: Arc B580 (12 GB, launch MSRP $249) at Q8_0, fully in VRAM at 8K context.
- Largest popular model that fits the RX 7900 XT: Qwen3.8 27B (28B) 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
SenseNova Loop 9B 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 (sensenova/SenseNova-Loop-9B), AMD specs. Model data last checked 2026-11-17; refreshed hourly.