Can I Run Mistral Small 4 on NVIDIA H100 80GB (PCIe)?
Written by Jakub Rusinowski · Last updated July 21, 2026
Yes, but it's tight — Mistral Small 4 119B-A6.5B at Q4_K_M needs 75.5 GB at 8K context (71.8 GB weights + 3.7 GB KV cache/overhead), leaving ~4.5 GB of the NVIDIA H100 80GB (PCIe)'s 80 GB, at ~92 tok/s (est.), with room for up to 16K context.
See what else this hardware can run →
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
NVIDIA H100 80GB (PCIe) Specs
| VRAM | 80 GB |
| Memory Bandwidth | 2000 GB/s |
Mistral Small 4 119B-A6.5B on the NVIDIA H100 80GB (PCIe): VRAM by quantization
| Quant | VRAM needed | Fits 80 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 241.7 GB | ✗ No | — | — |
| Q8_0 | 130.1 GB | ✗ No | — | — |
| Q6_K | 101.2 GB | ✗ No | — | — |
| Q5_K_M | 88 GB | ✗ No | — | — |
| Q4_K_M | 75.5 GB | ✓ Yes | 16K | — |
| Q3_K_M | 54.4 GB | ✓ Yes | 64K | — |
| Q2_K | 42.8 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 75.5 GB · 32K 84.1 GB ✗ · 128K 118.3 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? Mistral Small 4 119B-A6.5B on 64 GB of system RAM, CPU only: runs.
Mistral Small 4 Sizes That Fit the NVIDIA H100 80GB (PCIe) (at 8K context)
| Mistral Small 4 119B-A6.5B | Q4_K_M · 75.5 GB at 8K context · ~92 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
Can I run Mistral Small 4 on the NVIDIA H100 80GB (PCIe)?
Yes, but it's tight — Mistral Small 4 119B-A6.5B at Q4_K_M needs 75.5 GB at 8K context (71.8 GB weights + 3.7 GB KV cache/overhead), leaving ~4.5 GB of the NVIDIA H100 80GB (PCIe)'s 80 GB, at ~92 tok/s (est.), with room for up to 16K context.
What's the best Mistral Small 4 size for the NVIDIA H100 80GB (PCIe)?
Mistral Small 4 119B-A6.5B at Q4_K_M quantization needs 75.5 GB at 8K context (71.8 GB weights + 3.7 GB KV cache/overhead), estimated ~92 tokens/sec, up to 16K context.
Mistral Small 4 on Other GPUs
- Mistral Small 4 on NVIDIA A100 80GB (PCIe)
- Mistral Small 4 on Apple M2 Max
- Mistral Small 4 on Apple M1 Max
- Mistral Small 4 on Apple M5 Pro
- Mistral Small 4 on NVIDIA RTX PRO 6000 Blackwell
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? | Mistral Small 4 Model Page | NVIDIA H100 80GB (PCIe) GPU Page | Check Your Hardware