Can Qwen AgentWorld 35B A3B run on the L40S?
Yes. At 8K context the best fit is Q8_0, using about 35.4 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~270 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) | 13.1 GB Fits | 13.1 GB Fits | 13.6 GB Fits | 15.5 GB Fits | 768 |
| 3-bit (Q3_K_M) • | 16.5 GB Fits | 16.6 GB Fits | 17.0 GB Fits | 18.9 GB Fits | 598 |
| 4-bit (Q4_K_M) • | 21.6 GB Fits | 21.6 GB Fits | 22.1 GB Fits | 24.0 GB Fits | 451 |
| 5-bit (Q5_K_M) • | 25.6 GB Fits | 25.7 GB Fits | 26.1 GB Fits | 28.0 GB Fits | 377 |
| 6-bit (Q6_K) • | 28.2 GB Fits | 28.3 GB Fits | 28.8 GB Fits | 30.7 GB Fits | 341 |
| 8-bit (Q8_0) • | 35.3 GB Fits | 35.4 GB Fits | 35.9 GB Fits | 37.7 GB Fits | 270 |
| 16-bit (F16/BF16) • | 65.6 GB No | 65.6 GB No | 66.1 GB No | 68.0 GB No | — |
• real GGUF file size from unsloth/Qwen-AgentWorld-35B-A3B-GGUF. Speed is a bandwidth ceiling (864 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Qwen AgentWorld 35B A3B: RTX 5090 (32 GB, launch MSRP $1,999) at Q5_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the L40S: 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
Qwen AgentWorld 35B A3B on every GPU and Mac · Every model that runs on the L40S · Other models that fit 48 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 (Qwen/Qwen-AgentWorld-35B-A3B), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.