RTX 3090 24GBGünstige Wahl24 GB VRAM (+4)936 GB/s (+576)
B
Raises estimated decode speed by about 133%.67.6 tok/s Dekodierung
Raises estimated decode speed by about 133%.
ca. $1,499 MSRP
Can StarCoder2 15B run on RTX 4000 Ada 20GB?
YES — Runs Great
C55Usable
Estimated from fit model
StarCoder2 15B needs ~15.2 GB VRAM. RTX 4000 Ada 20GB has 20.0 GB. With Q5_K_M quantization, expect ~29 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: Balanced
Operating mode
Choose the run profile you care about
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
Q5_K_M (High quality) — 15.2 GB, 29.0 tok/s, Runs well
15.2 GB required20.0 GB available
76% VRAM used
Fit status
Runs well
Decode
29.0 tok/s
TTFT
6687 ms
Safe context
16K
Memory
15.2 GB / 20.0 GB
Memory breakdown
Weights10.8 GB
KV Cache1.2 GB
Runtime1.2 GB
Headroom2.0 GB
See how fast it feels
See how fast it feelsStarCoder2 15B on RTX 4000 Ada 20GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:
def quicksort(arr):
if len(arr) <= 1:
return arr
pivot = arr[len(arr) // 2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quicksort(left) + middle + quicksort(right)
# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers)) # [1, 1, 2, 3, 6, 8, 10]
The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
"""Sort a list using the quicksort algorithm.
Args:
arr: List of integers to sort.
Returns:
A new sorted list.
"""
if len(arr) <= 1:
return arr
pivot = arr[len(arr) // 2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quicksort(left) + middle + quicksort(right)
Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 29.0 tok/s decode · 6.7s TTFT (warm) · 72 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 29.0 tok/s | 3648 ms | 16K |
| Coding | C | Runs well | 29.0 tok/s | 6687 ms | 16K |
| Agentic Coding | C | Tight fit | 29.0 tok/s | 9727 ms | 16K |
| Reasoning | C | Runs well | 29.0 tok/s | 7903 ms | 16K |
| RAG | C | Tight fit | 29.0 tok/s | 12158 ms | 16K |
Inference speed
StarCoder2 15B inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for StarCoder2 15B at Q5_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~124 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
| RTX 5090 32GB | 32 GB | Q5_K_M | 123.8 | Fits |
| RTX 4090 24GB | 24 GB | Q5_K_M | 79.0 | Fits |
RX 7900 XTX 24GB | 24 GB | Q5_K_M | 71.3 | Fits |
| RTX 3090 24GB | 24 GB | Q5_K_M | 67.6 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q5_K_M | 64.4 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q5_K_M | 57.4 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q5_K_M | 47.8 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q5_K_M | 45.4 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q5_K_M | 32.8 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q5_K_M | 32.8 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q5_K_M | 24.7 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q5_K_M | 22.7 | Fits |
| RTX 4070 12GB | 12 GB | Q5_K_M | 21.2 | Heavy offload |
MacBook Pro M4 Pro 48GB | 48 GB | Q5_K_M | 20.0 | Fits |
| RTX 3060 12GB | 12 GB | Q5_K_M | 12.5 | Heavy offload |
| RTX 4060 8GB | 8 GB | Q5_K_M | 4.7 | Too big |
Estimates for single-stream decoding at Q5_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
Quantization options
How StarCoder2 15B (15B params) fits at each quantization level on RTX 4000 Ada 20GB (20.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C49 |
Q3_K_S | 3 | 7.4 GB | Low | C50 |
NVFP4 | 4 | 8.4 GB | Medium | C51 |
Q4_K_M | 4 | 9.2 GB | Medium | C52 |
Q5_K_M | 5 | 10.8 GB | High | C52 |
Q6_K | 6 | 12.3 GB | High | C52 |
Q8_0Best for your GPU | 8 | 16.1 GB | Very High | C51 |
F16 | 16 | 30.7 GB | Maximum | F0 |
Get started
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-Optionen
Hardware, die StarCoder2 15B gut ausführt
RTX 3090 24GBGünstige WahlRTX 4090 24GBBestes Preis-Leistungs-Verhältnis24 GB VRAM (+4)1008 GB/s (+648)
B
Raises estimated decode speed by about 172%.79 tok/s Dekodierung
Raises estimated decode speed by about 172%.
ca. $1,599 MSRP
RTX PRO 4000 Blackwell 24GBNVIDIA-Upgrade24 GB VRAM (+4)672 GB/s (+312)
B
Raises estimated decode speed by about 101%.58.2 tok/s Dekodierung
Raises estimated decode speed by about 101%.
ca. $1,599 MSRP
Frequently asked questions
Can RTX 4000 Ada 20GB run StarCoder2 15B?
Yes, RTX 4000 Ada 20GB can run StarCoder2 15B with a C grade (Runs well). Expected decode speed: 29.0 tok/s.
How much VRAM does StarCoder2 15B need?
StarCoder2 15B (15B parameters) requires approximately 15.2 GB of memory with Q5_K_M quantization.
What is the best quantization for StarCoder2 15B?
The recommended quantization for StarCoder2 15B is Q5_K_M, which balances quality and memory efficiency.
What speed will StarCoder2 15B run at on RTX 4000 Ada 20GB?
On RTX 4000 Ada 20GB, StarCoder2 15B achieves approximately 29.0 tokens per second decode speed with a time-to-first-token of 6687ms using Q5_K_M quantization.
Can RTX 4000 Ada 20GB run StarCoder2 15B for coding?
For coding workloads, StarCoder2 15B on RTX 4000 Ada 20GB receives a C grade with 29.0 tok/s and 16K context.
What context window can StarCoder2 15B use on RTX 4000 Ada 20GB?
On RTX 4000 Ada 20GB, StarCoder2 15B can safely use up to 16K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/starcoder2-15b-on-rtx-4000-ada-20gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: