Can Granite Vision 4.1 4B run on the RX 7600?
Yes. At 8K context the best fit is Q8_0, using about 4.6 GB of the 7.6 GB usable on the RX 7600. Estimated speed ceiling: ~80 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) | 2.3 GB Fits | 2.6 GB Fits | 4.5 GB Fits | 12.0 GB No | 192 |
| 3-bit (Q3_K_M) | 2.7 GB Fits | 3.0 GB Fits | 4.9 GB Fits | 12.4 GB No | 147 |
| 4-bit (Q4_K_M) • | 2.9 GB Fits | 3.2 GB Fits | 5.0 GB Fits | 12.5 GB No | 137 |
| 5-bit (Q5_K_M) • | 3.2 GB Fits | 3.5 GB Fits | 5.4 GB Fits | 12.9 GB No | 118 |
| 6-bit (Q6_K) • | 3.5 GB Fits | 3.8 GB Fits | 5.7 GB Fits | 13.2 GB No | 103 |
| 8-bit (Q8_0) • | 4.3 GB Fits | 4.6 GB Fits | 6.5 GB Fits | 14.0 GB No | 80 |
| 16-bit (F16/BF16) • | 7.2 GB Tight | 7.6 GB Tight | 9.4 GB No | 16.9 GB No | 42 |
• real GGUF file size from ibm-granite/granite-vision-4.1-4b-GGUF. Speed is a bandwidth ceiling (288 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Granite Vision 4.1 4B: Arc B580 (12 GB, launch MSRP $249) at F16, fully in VRAM at 8K context.
- Largest popular model that fits the RX 7600: Qwen3.5 9B (9.7B) at Q4_K_M, about 6.4 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 Vision 4.1 4B on every GPU and Mac · Every model that runs on the RX 7600 · Other models that fit 8 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-vision-4.1-4b), AMD specs. Model data last checked 2026-11-17; refreshed hourly.