StarCoder2 15B needs ~14.1 GB VRAM. RTX 3080 Ti 12GB has 12.0 GB. With Q5_K_M quantization, expect ~35 tok/s.
Operating mode
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
2.1 GB over capacity — needs offload or smaller quantization
Fit status
Very compromised (needs ~1.6 GB host RAM)
Decode
35.4 tok/s
TTFT
5474 ms
Safe context
4K
Memory
14.1 GB / 12.0 GB
Offload
20%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 20% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 1.6 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Very compromised (needs ~1.2 GB host RAM) | 38.8 tok/s | 2721 ms | 4K |
| Coding | D | Very compromised (needs ~1.6 GB host RAM) | 35.4 tok/s | 5474 ms | 4K |
| Agentic Coding | F | Too heavy | 29.7 tok/s | 9481 ms | 4K |
| Reasoning | D | Very compromised (needs ~1.6 GB host RAM) | 35.4 tok/s | 6470 ms | 4K |
| RAG | F | Too heavy | 29.7 tok/s | 11851 ms | 4K |
How StarCoder2 15B (15B params) fits at each quantization level on RTX 3080 Ti 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C54 |
Q3_K_S | 3 | 7.4 GB | Low | C53 |
NVFP4Best for your GPU | 4 | 8.4 GB | Medium | C53 |
Q4_K_M | 4 | 9.2 GB | Medium | F0 |
Q5_K_M | 5 | 10.8 GB | High | F0 |
Q6_K | 6 | 12.3 GB | High | F0 |
Q8_0 | 8 | 16.1 GB | Very High | F0 |
F16 | 16 | 30.7 GB | Maximum | F0 |
Copy-paste commands to run StarCoder2 15B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "bigcode/starcoder2-15b" \
--hf-file "starcoder2-15b-Q5_K_M.gguf" \
-c 4096 -ngl 99Upgrade options
RTX 5060 Ti 16GBBudget pickRemoves host-memory offload, which is usually the single biggest latency and throughput win.
Adds memory headroom for longer context windows and future model growth.
~$449 MSRP
RTX 4060 Ti 16GBBest valueRemoves host-memory offload, which is usually the single biggest latency and throughput win.
Adds memory headroom for longer context windows and future model growth.
~$499 MSRP
RTX 2000 Ada 16GBNVIDIA upgradeRemoves host-memory offload, which is usually the single biggest latency and throughput win.
Adds memory headroom for longer context windows and future model growth.
~$625 MSRP
RTX 4090 24GBBiggest leapRemoves host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 128%.
~$1,599 MSRP
Yes, RTX 3080 Ti 12GB can run StarCoder2 15B with a D grade (Very compromised (needs ~1.6 GB host RAM)). Expected decode speed: 35.4 tok/s.
StarCoder2 15B (15B parameters) requires approximately 14.1 GB of memory with Q5_K_M quantization.
The recommended quantization for StarCoder2 15B is Q5_K_M, which balances quality and memory efficiency.
On RTX 3080 Ti 12GB, StarCoder2 15B achieves approximately 35.4 tokens per second decode speed with a time-to-first-token of 5474ms using Q5_K_M quantization.
For coding workloads, StarCoder2 15B on RTX 3080 Ti 12GB receives a D grade with 35.4 tok/s and 4K context.
On RTX 3080 Ti 12GB, StarCoder2 15B can safely use up to 4K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/starcoder2-15b-on-rtx-3080-ti-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: