Can Baichuan 13B run on NVIDIA L40S 48GB?

YES — Runs Great

B70Good

○Estimated from fit model

Baichuan 13B needs ~27.3 GB VRAM. NVIDIA L40S 48GB has 48.0 GB. With Q5_K_M quantization, expect ~77 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q5_K_M (High quality) — 27.3 GB, 77.1 tok/s, Runs well

27.3 GB required48.0 GB available

57% VRAM used

Fit status

Runs well

Decode

77.1 tok/s

TTFT

2511 ms

Safe context

Memory

27.3 GB / 48.0 GB

Memory breakdown

Weights9.4 GB

KV Cache12.2 GB

Runtime0.9 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsBaichuan 13B on NVIDIA L40S 48GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.

Given information:
 - Speed = 60 mph (miles per hour)
 - Time = 2.5 hours

Formula: Distance = Speed x Time

Calculation:
 Distance = 60 mph x 2.5 h
 = 150 miles

The train travels 150 miles.

Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.

Breakdown:
 - First half: 1.25 hours at 60 mph = 75 miles
 - Stop: 20 minutes (no distance)
 - Second half: 1.25 hours at 60 mph = 75 miles

Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph

The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 77.1 tok/s decode · 2.5s TTFT (warm) · 193 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Runs well	77.1 tok/s	1369 ms	8K
Coding	B	Runs well	77.1 tok/s	2511 ms	8K
Agentic Coding	B	Tight fit	77.1 tok/s	3652 ms	8K
Reasoning	B	Runs well	77.1 tok/s	2967 ms	8K
RAG	B	Tight fit	77.1 tok/s	4565 ms	8K

Quantization options

How Baichuan 13B (13B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.1 GB	Low	B58
Q3_K_S	3	6.4 GB	Low	B58
NVFP4	4	7.3 GB	Medium	B58
Q4_K_M	4	7.9 GB	Medium	B58
Q5_K_M	5	9.4 GB	High	B59
Q6_K	6	10.7 GB	High	B59
Q8_0	8	13.9 GB	Very High	B60
F16Best for your GPU	16	26.7 GB	Maximum	B64

Get started

Copy-paste commands to run Baichuan 13B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "baichuan-inc/Baichuan-13B-Chat" \
 --hf-file "Baichuan-13B-Chat-Q5_K_M.gguf" \
 -c 4096 -ngl 99

Frequently asked questions

See all results for NVIDIA L40S 48GB See all hardware for Baichuan 13B

URL: https://willitrunai.com/can-run/baichuan-13b-on-l40s-48gb