Can Baichuan 13B run on NVIDIA A800 80GB?

YES — Runs Great

B66Good

○Estimated from fit model

Baichuan 13B needs ~30.8 GB VRAM. NVIDIA A800 80GB has 80.0 GB. With Q5_K_M quantization, expect ~165 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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) — 30.8 GB, 164.5 tok/s, Runs well

30.8 GB required80.0 GB available

39% VRAM used

Fit status

Runs well

Decode

164.5 tok/s

TTFT

1177 ms

Safe context

Memory

30.8 GB / 80.0 GB

Memory breakdown

Weights9.4 GB

KV Cache12.2 GB

Runtime1.2 GB

Headroom8.0 GB

See how fast it feels

See how fast it feelsBaichuan 13B on NVIDIA A800 80GB
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: 164.5 tok/s decode · 1.2s TTFT (warm) · 411 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	164.5 tok/s	642 ms	8K
Coding	B	Runs well	164.5 tok/s	1177 ms	8K
Agentic Coding	B	Runs well	164.5 tok/s	1712 ms	8K
Reasoning	B	Runs well	164.5 tok/s	1391 ms	8K
RAG	B	Runs well	164.5 tok/s	2140 ms	8K

Quantization options

How Baichuan 13B (13B params) fits at each quantization level on NVIDIA A800 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.1 GB	Low	B56
Q3_K_S	3	6.4 GB	Low	B56
NVFP4	4

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 A800 80GB See all hardware for Baichuan 13B

URL: https://willitrunai.com/can-run/baichuan-13b-on-a800-80gb

⇱