Can Qwen3.5 35B A3B run on the A100 40GB?
Yes. At 8K context the best fit is Q6_K, using about 27.9 GB of the 38.0 GB usable on the A100 40GB. Estimated speed ceiling: ~646 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) | 13.5 GB Fits | 13.6 GB Fits | 14.1 GB Fits | 15.9 GB Fits | 1382 |
| 3-bit (Q3_K_M) • | 16.2 GB Fits | 16.3 GB Fits | 16.7 GB Fits | 18.6 GB Fits | 1139 |
| 4-bit (Q4_K_M) • | 21.5 GB Fits | 21.5 GB Fits | 22.0 GB Fits | 23.9 GB Fits | 846 |
| 5-bit (Q5_K_M) • | 25.4 GB Fits | 25.5 GB Fits | 25.9 GB Fits | 27.8 GB Fits | 710 |
| 6-bit (Q6_K) • | 27.8 GB Fits | 27.9 GB Fits | 28.4 GB Fits | 30.2 GB Fits | 646 |
| 8-bit (Q8_0) • | 35.3 GB Tight | 35.4 GB Tight | 35.9 GB Tight | 37.7 GB Tight | 505 |
| 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/Qwen3.5-35B-A3B-GGUF. Speed is a bandwidth ceiling (1555 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Qwen3.5 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 A100 40GB: Qwen3.6 35B A3B (36B, MoE) at Q6_K, about 29.0 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
Qwen3.5 35B A3B on every GPU and Mac · Every model that runs on the A100 40GB · Other models that fit 48 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (Qwen/Qwen3.5-35B-A3B), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.