Code Llama 34B Instruct on NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 handles Code Llama 34B Instruct well at 22 tok/s at Q4_K_M. A solid choice for this model.
Model Size
33.7B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows Code Llama 34B Instruct performance at a different quality level on NVIDIA GeForce RTX 4090.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q4_K_M | 22 tok/s | 400ms | ✓ Yes | Good | estimated |
Notes
Q4_K_M
Q4 at 19GB fits on 4090 with 5GB headroom. Surpassed by Qwen 2.5 Coder 32B but still solid.
About Code Llama 34B Instruct
Code Llama 34B Instruct (33.7B) is a coding, ai coding model. Meta's dedicated 34B coding model. Still competitive for code generation but being surpassed by newer models like Qwen 2.5 Coder 32B. Shorter context window (16K) is a limitation for large codebases.
View all Code Llama 34B Instruct 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