Can I Run Qwen 3.5 on NVIDIA H100 80GB (PCIe)?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 21 lipca 2026
Yes, but it's tight — Qwen 3.5 122B-A10B at Q4_K_M needs 77.3 GB at 8K context (73.7 GB weights + 3.6 GB KV cache/overhead), leaving ~2.7 GB of the NVIDIA H100 80GB (PCIe)'s 80 GB, at ~151 tok/s (est.), with room for up to 8K context.
See what else this hardware can run →
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
NVIDIA H100 80GB (PCIe) Specs
| VRAM | 80 GB |
| Memory Bandwidth | 2000 GB/s |
Qwen 3.5 122B-A10B on the NVIDIA H100 80GB (PCIe): VRAM by quantization
| Quant | VRAM needed | Fits 80 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 247.7 GB | ✗ No | — | — |
| Q8_0 | 133.3 GB | ✗ No | — | — |
| Q6_K | 103.7 GB | ✗ No | — | — |
| Q5_K_M | 90.1 GB | ✗ No | — | — |
| Q4_K_M | 77.3 GB | ✓ Yes | 8K | — |
| Q3_K_M | 55.7 GB | ✓ Yes | 64K | — |
| Q2_K | 43.8 GB | ✓ Yes | 64K | — |
Assumes an 8K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 80 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA H100 80GB (PCIe): 8K 77.3 GB · 32K 85.9 GB ✗ · 128K 120.1 GB ✗. Past 32K it no longer fits 80 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? Qwen 3.5 122B-A10B on 128 GB of system RAM, CPU only: runs.
Qwen 3.5 Sizes That Fit the NVIDIA H100 80GB (PCIe) (at 8K context)
| Qwen 3.5 122B-A10B | Q4_K_M · 77.3 GB at 8K context · ~151 tok/s (est.) |
| Qwen 3.5 35B-A3B | Q4_K_M · 23.8 GB at 8K context · ~259 tok/s (est.) |
| Qwen 3.5 27B | Q4_K_M · 18.8 GB at 8K context · ~81 tok/s (est.) |
| Qwen 3.5 9B | Q4_K_M · 6.5 GB at 8K context · ~181 tok/s (est.) |
| Qwen 3.5 4B | Q4_K_M · 3.5 GB at 8K context · ~267 tok/s (est.) |
| Qwen 3.5 2B | Q4_K_M · 2.7 GB at 8K context · ~315 tok/s (est.) |
| Qwen 3.5 0.8B | Q4_K_M · 1.8 GB at 8K context · ~372 tok/s (est.) |
At 2 hrs/day, buying (~$25,000) beats renting at $0.77/hr after about 45.1 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Is the NVIDIA H100 80GB (PCIe) enough to run Qwen 3.5 locally?
Yes, but it's tight — Qwen 3.5 122B-A10B at Q4_K_M needs 77.3 GB at 8K context (73.7 GB weights + 3.6 GB KV cache/overhead), leaving ~2.7 GB of the NVIDIA H100 80GB (PCIe)'s 80 GB, at ~151 tok/s (est.), with room for up to 8K context.
What's the best Qwen 3.5 size for the NVIDIA H100 80GB (PCIe)?
Qwen 3.5 122B-A10B at Q4_K_M quantization needs 77.3 GB at 8K context (73.7 GB weights + 3.6 GB KV cache/overhead), estimated ~151 tokens/sec, up to 8K context.
Every Qwen 3.5 size on the NVIDIA H100 80GB (PCIe)
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| Qwen 3.5 397B-A17B | 139 GB | Does not fit | — |
| Qwen 3.5 122B-A10B | 77.3 GB | Runs | ~151 tok/s |
| Qwen 3.5 35B-A3B | 23.8 GB | Runs | ~259 tok/s |
| Qwen 3.5 27B | 18.8 GB | Runs | ~81 tok/s |
| Qwen 3.5 9B | 6.5 GB | Runs | ~181 tok/s |
| Qwen 3.5 4B | 3.5 GB | Runs | ~267 tok/s |
| Qwen 3.5 2B | 2.7 GB | Runs | ~315 tok/s |
| Qwen 3.5 0.8B | 1.8 GB | Runs | ~372 tok/s |
Qwen 3.5 on Other GPUs
Popular Models on the NVIDIA H100 80GB (PCIe)
VRAM Tier
Troubleshooting
- CUDA out of memory — why it happens and how to fix it
- Which GGUF quant should I download? (Q4 vs Q5 vs Q8)
Buying Guide
← Can I Run It? | Qwen 3.5 Model Page | NVIDIA H100 80GB (PCIe) GPU Page | VRAM calculator | Check Your Hardware