LLM Roofline
NVIDIA · PCIE · Backend: llama.cpp

NVIDIA RTX 5060 Ti (16 GB) — LLM Sizing & Speed Matrix

Most affordable 16 GB Blackwell card; great budget fit for 14B Q4_K_M coding assistants.

Reference Pricing
$449 Street
Usable Memory
15 GiB
Memory Bandwidth
448 GB/s (80% eff.)
FP16 Compute
47.4 TFLOPS
Roofline Ridge
82.0 FLOP/B
Power (Load / Idle)
180W / 22W

Buy or Rent NVIDIA RTX 5060 Ti (16 GB)

Vendor & Cloud Links
RTX 5060 Ti 16 GB on Amazon
Amazon · Direct Hardware
↗
NVIDIA RTX Cards on Newegg
Newegg · Direct Hardware
↗

All 32 Open-Weight Models on NVIDIA RTX 5060 Ti (16 GB) (Q4_K_M @ 32k)

Model Status Weights Total @ 32k Decode TTFT (4k) Max Safe Ctx
Phi-4 14B COMFORTABLE 8.5 GiB 13.0 GiB 28.8 tok/s 4.37s 16k
Gemma 3 12B IT COMFORTABLE 7.0 GiB 10.6 GiB 35.7 tok/s 3.66s 102k
Qwen3 8B COMFORTABLE 4.7 GiB 10.5 GiB 36.2 tok/s 2.49s 40k
Llama 3.1 8B Instruct COMFORTABLE 4.6 GiB 9.9 GiB 38.7 tok/s 2.42s 73k
Qwen2.5 7B Instruct COMFORTABLE 4.4 GiB 7.4 GiB 54.5 tok/s 2.27s 32k
Gemma 3 4B IT COMFORTABLE 2.5 GiB 4.4 GiB 100.1 tok/s 1.31s 128k
Qwen3 14B TIGHT 8.5 GiB 15.0 GiB 24.7 tok/s 4.39s 32k
DeepSeek-R1 671B OOM 386.4 GiB 390.3 GiB OOM — OOM
DeepSeek-V3 671B OOM 386.4 GiB 390.3 GiB OOM — OOM
Llama 3.1 405B Instruct OOM 233.8 GiB 252.5 GiB OOM — OOM
Llama 4 Maverick 400B-A17B OOM 231.5 GiB 239.0 GiB OOM — OOM
Qwen3 235B-A22B OOM 135.4 GiB 142.6 GiB OOM — OOM
Mixtral 8x22B Instruct OOM 81.2 GiB 89.8 GiB OOM — OOM
Command A 111B OOM 63.9 GiB 69.1 GiB OOM — OOM
Llama 4 Scout 109B-A17B OOM 62.8 GiB 70.2 GiB OOM — OOM
Qwen2.5 72B Instruct OOM 41.9 GiB 53.7 GiB OOM — OOM
DeepSeek-R1 Distill Llama 70B OOM 40.7 GiB 52.5 GiB OOM — OOM
Llama 3.3 70B Instruct OOM 40.7 GiB 52.5 GiB OOM — OOM
Llama 3.1 70B Instruct OOM 40.7 GiB 52.5 GiB OOM — OOM
Llama-3.3 Nemotron Super 49B OOM 28.7 GiB 36.7 GiB OOM — OOM
Mixtral 8x7B Instruct OOM 26.9 GiB 32.2 GiB OOM — OOM
Qwen3 32B OOM 18.9 GiB 28.3 GiB OOM — OOM
Qwen2.5 Coder 32B OOM 18.9 GiB 28.3 GiB OOM — OOM
DeepSeek-R1 Distill Qwen 32B OOM 18.9 GiB 28.3 GiB OOM — OOM
QwQ 32B Reasoning OOM 18.9 GiB 28.3 GiB OOM — OOM
GLM-4 32B 0414 OOM 18.6 GiB 22.1 GiB OOM — OOM
Qwen3 30B-A3B OOM 17.6 GiB 21.6 GiB OOM — OOM
Gemma 3 27B IT OOM 15.8 GiB 20.2 GiB OOM — OOM
Mistral Small 3.1 24B OOM 13.8 GiB 20.3 GiB OOM — 2k
Codestral 22B OOM 12.8 GiB 21.4 GiB OOM — 5k
Qwen2.5 14B Instruct OOM 8.5 GiB 16.0 GiB OOM — 27k
DeepSeek-R1 Distill Qwen 14B OOM 8.5 GiB 16.0 GiB OOM — 27k

Interactive NVIDIA RTX 5060 Ti (16 GB) Simulator

14.7B Dense · GQA
448 GB/s · 47.4 TFLOPS
3. Weight Quantization 4.85 bpw
4. KV Cache
32,768 tok
Compute Roofline
OUT OF MEMORY (OOM) Memory-Bandwidth Bound
Max Safe Ctx: 16k
Memory Allocation Footprint 16.17 / 15.00 GiB usable
Weights: 8.47 GiB KV Cache: 6.25 GiB Overhead: 1.45 GiB Headroom: -1.17 GiB
Decode Speed
22.7
tok/s (batch=1)
Prefill Speed
946
prompt tok/s
TTFT Latency
4.37s
for 4,096 tok
Active Params
14.7B
of 14.7B total
llama.cpp Server Command 
llama-server -hf microsoft/phi-4:Q4_K_M -ngl 99 -fa on -c 32768 --port 8080
Context KV Cache Total VRAM Decode Status
4k 0.78 GiB 10.35 GiB 36.1 tok/s COMFORTABLE
8k 1.56 GiB 11.48 GiB 33.3 tok/s COMFORTABLE
16k 3.13 GiB 13.04 GiB 28.8 tok/s COMFORTABLE

Buy-vs-Cloud-vs-API Monthly TCO Break-Even

USE SERVERLESS API
Own Hardware/mo
$16.64
198.4h active + power
Cloud GPU/mo
$203.07
@$0.89/hr spot/pod
Serverless API/mo
$5.60
API cheaper

Recommended Hardware & Cloud Deployment

Contextual to fit status

Hardware FAQ — NVIDIA RTX 5060 Ti (16 GB)

How much usable VRAM / GPU memory does NVIDIA RTX 5060 Ti (16 GB) actually provide for LLMs?

NVIDIA RTX 5060 Ti (16 GB) provides 15 GiB usable VRAM after subtracting 1.0 GiB driver/display overhead.

What is the largest Q4_K_M model NVIDIA RTX 5060 Ti (16 GB) can run at 32k context?

With Q4_K_M weights and FP16 KV cache at 32k context, the largest fitting model in our verified catalog on NVIDIA RTX 5060 Ti (16 GB) is Phi-4 14B (14.7B total).