32 GB VRAM (+8)1792 GB/s (+1492)
A
Raises estimated decode speed by about 719%.126.9 tok/s decode
Raises estimated decode speed by about 719%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Can Baichuan 13B run on NVIDIA L4 24GB?
YES — With Offload
B64Good
○Estimated from fit model
Baichuan 13B needs ~24.9 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q5_K_M quantization, expect ~15 tok/s.
Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: StandardBottleneck: Host offload
Share:
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.
Select quantization to explore
Q5_K_M (High quality) — 24.9 GB, 15.5 tok/s, Runs with offload (needs ~0.3 GB host RAM)
24.9 GB required24.0 GB available
104% VRAM needed
0.9 GB over capacity — needs offload or smaller quantization
Fit status
Runs with offload (needs ~0.3 GB host RAM)
Decode
15.5 tok/s
TTFT
12466 ms
Safe context
8K
Memory
24.9 GB / 24.0 GB
Memory breakdown
Weights9.4 GB
KV Cache12.2 GB
Runtime0.9 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelsBaichuan 13B on NVIDIA L4 24GB
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: 15.5 tok/s decode · 12.5s TTFT (warm) · 39 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Best improvement path
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 22.3 tok/s | 4733 ms | 8K |
| Coding | B | Runs with offload | 14.8 tok/s | 13090 ms | 8K |
| Agentic Coding | F | Too heavy | 6.7 tok/s | 42031 ms | 8K |
| Reasoning | B | Runs with offload (needs ~0.3 GB host RAM) | 15.5 tok/s | 14733 ms | 8K |
| RAG | F | Too heavy | 6.7 tok/s | 52539 ms | 8K |
Quantization options
How Baichuan 13B (13B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.1 GB | Low | B62 |
Q3_K_S | 3 | 6.4 GB | Low | B62 |
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 99Upgrade options
Hardware that runs Baichuan 13B well
32 GB VRAM (+8)896 GB/s (+596)
A
Raises estimated decode speed by about 429%.82 tok/s decode
Raises estimated decode speed by about 429%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
32 GB VRAM (+8)576 GB/s (+276)
A
Raises estimated decode speed by about 224%.50.2 tok/s decode
Raises estimated decode speed by about 224%.
Adds memory headroom for longer context windows and future model growth.
~$4,000 MSRP