6 GB VRAM (+2)336 GB/s (+208)
C
Adds memory headroom for longer context windows and future model growth.42 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$229 MSRP
Can StarCoder2 3B run on GTX 1650 4GB?
YES — With Offload
C49Usable
○Estimated from fit model
StarCoder2 3B needs ~3.9 GB VRAM. GTX 1650 4GB has 4.0 GB. With Q4_K_M quantization, expect ~35 tok/s.
Runtime: OllamaCapacity: OffloadBandwidth: Very lowStack: BasicBottleneck: Memory bandwidth
Share:
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
Q4_K_M (Medium quality) — 3.9 GB, 38.0 tok/s, Runs with offload
3.9 GB required4.0 GB available
98% VRAM used
Fit status
Runs with offload
Decode
38.0 tok/s
TTFT
5090 ms
Safe context
16K
Memory
3.9 GB / 4.0 GB
Memory breakdown
Weights1.8 GB
KV Cache0.5 GB
Runtime1.2 GB
Headroom0.4 GB
See how fast it feels
See how fast it feelsStarCoder2 3B on GTX 1650 4GB
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: 38.0 tok/s decode · 5.1s TTFT (warm) · 95 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
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.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Best improvement path
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Tight fit | 35.0 tok/s | 3020 ms | 16K |
| Coding | C | Runs with offload | 35.0 tok/s | 5536 ms | 16K |
| Agentic Coding | D | Very compromised | 21.3 tok/s | 13242 ms | 16K |
| Reasoning | C | Runs with offload | 35.0 tok/s | 6542 ms | 16K |
| RAG | D | Very compromised | 21.3 tok/s | 16552 ms | 16K |
Quantization options
How StarCoder2 3B (3B params) fits at each quantization level on GTX 1650 4GB (4.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.2 GB | Low | C54 |
Q3_K_S | 3 | 1.5 GB | Low | C54 |
NVFP4 | 4 |
Get started
Copy-paste commands to run StarCoder2 3B on your machine.
Run
ollama run starcoder2:3bUpgrade options
Hardware that runs StarCoder2 3B well
6 GB VRAM (+2)192 GB/s (+64)
C
Adds memory headroom for longer context windows and future model growth.42 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$249 MSRP
6 GB VRAM (+2)288 GB/s (+160)
C
Adds memory headroom for longer context windows and future model growth.42 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$279 MSRP