MacBook Pro M4 Max 36GBBudget pick
36 GB Unified (+12)410 GB/s (+110)
A
Raises estimated decode speed by about 44%.65.9 tok/s decode
Raises estimated decode speed by about 44%.
~$2,499 MSRP
Can Baichuan 7B run on NVIDIA L4 24GB?
YES — Runs Great
B70Good
○Estimated from fit model
Baichuan 7B needs ~15.7 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~46 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: Balanced
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
Q4_K_M (Medium quality) — 15.7 GB, 45.7 tok/s, Runs well
15.7 GB required24.0 GB available
65% VRAM used
Fit status
Runs well
Decode
45.7 tok/s
TTFT
4239 ms
Safe context
8K
Memory
15.7 GB / 24.0 GB
Memory breakdown
Weights4.3 GB
KV Cache7.8 GB
Runtime1.2 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelsBaichuan 7B 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: 45.7 tok/s decode · 4.2s TTFT (warm) · 114 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 | 45.7 tok/s | 2312 ms | 8K |
| Coding | B | Runs well | 45.7 tok/s | 4239 ms | 8K |
| Agentic Coding | B | Runs with offload | 45.7 tok/s | 6166 ms | 8K |
| Reasoning | B | Runs well | 45.7 tok/s | 5010 ms | 8K |
| RAG | B | Runs with offload | 45.7 tok/s | 7708 ms | 8K |
Quantization options
How Baichuan 7B (7B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | B60 |
Q3_K_S | 3 | 3.4 GB | Low | B61 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Baichuan 7B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "baichuan-inc/Baichuan-7B" \
--hf-file "Baichuan-7B-Q4_K_M.gguf" \
-c 4096 -ngl 99Upgrade options