RX 7900 XT 20GBBest value
20 GB VRAM (+4)800 GB/s (+480)
C
Raises estimated decode speed by about 101%.98 tok/s decode
Raises estimated decode speed by about 101%.
Adds memory headroom for longer context windows and future model growth.
~$899 MSRP
Can starcoder2 7b run on NVIDIA T4 16GB?
YES — Runs Great
C50Usable
○Estimated from fit model
starcoder2 7b needs ~7.9 GB VRAM. NVIDIA T4 16GB has 16.0 GB. With Q4_K_M quantization, expect ~49 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: Balanced
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) — 7.9 GB, 48.7 tok/s, Runs well
7.9 GB required16.0 GB available
49% VRAM used
Fit status
Runs well
Decode
48.7 tok/s
TTFT
3974 ms
Safe context
174K
Memory
7.9 GB / 16.0 GB
Memory breakdown
Weights4.3 GB
KV Cache0.8 GB
Runtime1.2 GB
Headroom1.6 GB
See how fast it feels
See how fast it feelsstarcoder2 7b on NVIDIA T4 16GB
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: 48.7 tok/s decode · 4.0s TTFT (warm) · 122 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
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
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 48.7 tok/s | 2168 ms | 174K |
| Coding | C | Runs well | 48.7 tok/s | 3974 ms | 174K |
| Agentic Coding | C | Runs well | 48.7 tok/s | 5781 ms | 174K |
| Reasoning | C | Runs well | 48.7 tok/s | 4697 ms | 174K |
| RAG | C | Runs well | 48.7 tok/s | 7226 ms | 174K |
Quantization options
How starcoder2 7b (7B params) fits at each quantization level on NVIDIA T4 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | C46 |
Q3_K_S | 3 | 3.4 GB | Low | C47 |
NVFP4 | 4 |
Get started
Copy-paste commands to run starcoder2 7b on your machine.
Run
lms load hf-quantfactory--starcoder2-7b-gguf && lms server startUpgrade options
