Can Hermes 3 Llama 3.2 3B run on the 2x RTX 4090?
Yes. At 8K context the best fit is F16, using about 7.5 GB of the 45.6 GB usable on the 2x RTX 4090. Estimated speed ceiling: ~157 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) • | 2.4 GB Fits | 2.8 GB Fits | 5.4 GB Fits | 15.9 GB Fits | 739 |
| 3-bit (Q3_K_M) • | 2.7 GB Fits | 3.1 GB Fits | 5.7 GB Fits | 16.2 GB Fits | 597 |
| 4-bit (Q4_K_M) • | 3.0 GB Fits | 3.4 GB Fits | 6.0 GB Fits | 16.5 GB Fits | 499 |
| 5-bit (Q5_K_M) • | 3.2 GB Fits | 3.7 GB Fits | 6.3 GB Fits | 16.8 GB Fits | 434 |
| 6-bit (Q6_K) • | 3.5 GB Fits | 4.0 GB Fits | 6.6 GB Fits | 17.1 GB Fits | 381 |
| 8-bit (Q8_0) • | 4.3 GB Fits | 4.7 GB Fits | 7.3 GB Fits | 17.8 GB Fits | 295 |
| 16-bit (F16/BF16) • | 7.1 GB Fits | 7.5 GB Fits | 10.1 GB Fits | 20.6 GB Fits | 157 |
• real GGUF file size from bartowski/Hermes-3-Llama-3.2-3B-GGUF. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Hermes 3 Llama 3.2 3B: Arc B580 (12 GB, launch MSRP $249) at F16, fully in VRAM at 8K context.
- Largest popular model that fits the 2x RTX 4090: Qwen3.6 35B A3B (36B, MoE) at Q8_0, about 36.2 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
Hermes 3 Llama 3.2 3B on every GPU and Mac · Every model that runs on the 2x RTX 4090 · Try other settings in the calculator
Data: Hugging Face Hub (NousResearch/Hermes-3-Llama-3.2-3B), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.