NVIDIA

RTX 3050 Laptop GPU

Rent in the cloud

Where to buyLDLC Materiel.net TopAchat Cybertek Grosbill Rue du Commerce Amazon

4 Go

VRAM

—

Best generation

—

Efficiency (ref.)

—

Elec. cost / M tokens (ref.) · 0,25 €/kWh

What this card can run

Qwen3.5 0.8B Q4_K_M

0.58 Go

Not measured

Qwen3.5 2B Q4_K_M

1.4 Go

Not measured

Llama 3.2 3B Instruct Q4_K_M

2.02 Go

Doesn't fit in VRAM

Qwen3.5 4B Q4_K_M

3.01 Go

Doesn't fit in VRAM

Qwen2.5 7B Instruct Q4_K_M

4.68 Go

Doesn't fit in VRAM

Qwen2.5 Coder 7B Q4_K_M

4.68 Go

Doesn't fit in VRAM

Meta Llama 3.1 8B Instruct Q4_K_M

4.92 Go

Doesn't fit in VRAM

Qwen2.5 14B Instruct Q4_K_M

8.99 Go

Doesn't fit in VRAM

DeepSeek R1 Distill Qwen 14B Q4_K_M

8.99 Go

Doesn't fit in VRAM

Qwen2.5 Coder 14B Q4_K_M

8.99 Go

Doesn't fit in VRAM

Phi-4 Q4_K_M

9.05 Go

Doesn't fit in VRAM

Smooth ≥ 60 tok/s (faster than you read) · Comfortable 30-60 · Slow < 30 · "Doesn't fit" = model size + 2 GB headroom > VRAM (CPU offloading is excluded from the protocol: the numbers would be meaningless).

Measurements by model

No runs for this card yet. Your move: run the bench.

VRAM used = peak system GPU memory during the run (includes the OS, roughly 0.5–1 GB more than the model alone).