DeepSeek Coder V2 Lite 16B on NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 runs DeepSeek Coder V2 Lite 16B excellently at 55 tok/s at Q5_K_M. This is a strong pairing.
Model Size
15.7B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows DeepSeek Coder V2 Lite 16B performance at a different quality level on NVIDIA GeForce RTX 4090.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 55 tok/s | 100ms | ✓ Yes | Excellent | estimated |
Notes
Q5_K_M
Q5 at 10.9GB leaves 13GB free on 4090. Lightning fast for a coding model. MoE efficiency is impressive.
About DeepSeek Coder V2 Lite 16B
DeepSeek Coder V2 Lite 16B (15.7B) is a coding, ai coding, ai building model. MoE architecture — 15.7B total, ~2.4B active per token. Excellent code generation and completion. Extremely fast inference despite total param count. One of the best coding models for its effective size.
View all DeepSeek Coder V2 Lite 16B hardware options →About NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 has 24 GB at 1008 GB/s. Street price: $1,799.
See all models NVIDIA GeForce RTX 4090 can run →Builds with NVIDIA GeForce RTX 4090
Source: Community benchmarks (2026-01-15)
Data last updated: 2026-03-01