Can I Run Yi 1.5 34B Chat on NVIDIA L40S?
Written by Jakub Rusinowski · Last updated July 21, 2026
Yes. Yi 1.5 34B Chat needs 23.6 GB at 8K context (20.8 GB weights + 2.8 GB KV cache/overhead) at Q4_K_M and the NVIDIA L40S has 48 GB, leaving about 24.4 GB of headroom, at roughly 34 tok/s (estimated) with room for up to 16K of context.
See what else this hardware can run →
The numbers
| Model | Yi 1.5 34B Chat |
| Parameters | 34B |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 23.6 GB |
| NVIDIA L40S VRAM | 48 GB |
| Verdict | Runs |
| Max context | 16K |
| Estimated speed | ~34 tok/s |
Yi 1.5 34B Chat on the NVIDIA L40S: VRAM by quantization
| Quant | VRAM needed | Fits 48 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 71.6 GB | ✗ No | — | — |
| Q8_0 | 39.4 GB | ✓ Yes | 16K | — |
| Q6_K | 31 GB | ✓ Yes | 16K | — |
| Q5_K_M | 27.2 GB | ✓ Yes | 16K | — |
| Q4_K_M | 23.6 GB | ✓ Yes | 16K | — |
| Q3_K_M | 17.5 GB | ✓ Yes | 16K | — |
| Q2_K | 14.1 GB | ✓ Yes | 16K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 48 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 L40S: 8K 23.6 GB · 31K 29.4 GB. Every window this model publishes still fits 48 GB.
What to do next
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
No compatible GPU? Yi 1.5 34B Chat on 32 GB of system RAM, CPU only: runs comfortably.
Running Yi 1.5 34B Chat on this card:
At 2 hrs/day, buying (~$7,499) beats renting at $0.34/hr after about 30.6 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.
Other Yi 1.5 Family sizes on the NVIDIA L40S
- Yi 1.5 9B Chat — runs (6.9 GB)
Yi 1.5 34B Chat on nearby hardware
- Apple M3 Pro (36 GB) — runs
All Yi 1.5 Family sizes on the NVIDIA L40S | Yi 1.5 34B Chat model page | NVIDIA L40S GPU page | VRAM calculator | Check your hardware