Can SingVL S1 4B run on the RX 9070 XT?
Yes. At 8K context the best fit is F16, using about 9.0 GB of the 15.2 GB usable on the RX 9070 XT. Estimated speed ceiling: ~76 tokens/sec.
+ 0.6 GB with image input. The figures on this page are for text only. Sending images also loads the vision projector (mmproj) file: F16 at 8K context then needs about 9.6 GB (still fits). Calculator with image input on.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 2.8 GB Fits | 2.9 GB Fits | 3.7 GB Fits | 6.7 GB Fits | 334 |
| 3-bit (Q3_K_M) • | 3.1 GB Fits | 3.2 GB Fits | 4.0 GB Fits | 7.0 GB Fits | 283 |
| 4-bit (Q4_K_M) • | 3.5 GB Fits | 3.6 GB Fits | 4.4 GB Fits | 7.4 GB Fits | 236 |
| 5-bit (Q5_K_M) • | 3.9 GB Fits | 4.0 GB Fits | 4.7 GB Fits | 7.7 GB Fits | 208 |
| 6-bit (Q6_K) • | 4.2 GB Fits | 4.3 GB Fits | 5.1 GB Fits | 8.1 GB Fits | 185 |
| 8-bit (Q8_0) • | 5.2 GB Fits | 5.3 GB Fits | 6.0 GB Fits | 9.0 GB Fits | 143 |
| 16-bit (F16/BF16) • | 8.8 GB Fits | 9.0 GB Fits | 9.7 GB Fits | 12.7 GB Fits | 76 |
• real GGUF file size from maternion/SingVL-S1-4B-GGUF. Speed is a bandwidth ceiling (640 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs SingVL S1 4B: Arc B580 (12 GB, launch MSRP $249) at F16, fully in VRAM at 8K context.
- Largest popular model that fits the RX 9070 XT: gpt-oss 20B (21B, MoE) at Q8_0, about 12.3 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
SingVL S1 4B on every GPU and Mac · Every model that runs on the RX 9070 XT · Other models that fit 16 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 (inclusionAI/SingVL_S1_4B), AMD specs. Model data last checked 2026-11-17; refreshed hourly.