MacBook Pro M4 Max 48GBGünstige Wahl
48 GB Unified (+16)
B
This setup is broadly balanced for this model.71.4 tok/s Dekodierung
ca. $2,499 MSRP
Can Gemma 4 E2B run on RTX 5090 32GB?
YES — Runs Great
B70Good
Estimated from fit model
Gemma 4 E2B needs ~7.7 GB VRAM. RTX 5090 32GB has 32.0 GB. With Q4_K_M quantization, expect ~97 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: 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
Q4_K_M (Medium quality) — 7.7 GB, 96.9 tok/s, Runs well
7.7 GB required32.0 GB available
24% VRAM used
Fit status
Runs well
Decode
96.9 tok/s
TTFT
1998 ms
Safe context
128K
Memory
7.7 GB / 32.0 GB
Memory breakdown
Weights3.1 GB
KV Cache0.5 GB
Runtime0.9 GB
Headroom3.2 GB
See how fast it feels
See how fast it feelsGemma 4 E2B on RTX 5090 32GB
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: 96.9 tok/s decode · 2.0s TTFT (warm) · 242 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 | B | Runs well | 96.9 tok/s | 1090 ms | 128K |
| Coding | B | Runs well | 96.9 tok/s | 1998 ms | 128K |
| Agentic Coding | A | Runs well | 96.9 tok/s | 2906 ms | 128K |
| Reasoning | B | Runs well | 96.9 tok/s | 2361 ms | 128K |
| RAG | A | Runs well | 96.9 tok/s | 3633 ms | 128K |
Quantization options
How Gemma 4 E2B (5.099999904632568B params) fits at each quantization level on RTX 5090 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.0 GB | Low | B66 |
Q3_K_S | 3 | 2.5 GB | Low | B66 |
NVFP4 | 4 | 2.9 GB | Medium | B66 |
Q4_K_M | 4 | 3.1 GB | Medium | B66 |
Q5_K_M | 5 | 3.7 GB | High | B66 |
Q6_K | 6 | 4.2 GB | High | B66 |
Q8_0 | 8 | 5.5 GB | Very High | B67 |
F16Best for your GPU | 16 | 10.5 GB | Maximum | B69 |
Get started
Copy-paste commands to run Gemma 4 E2B on your machine.
Run
ollama run gemma4:e2bUpgrade-Optionen
Hardware, die Gemma 4 E2B gut ausführt
Frequently asked questions
Can RTX 5090 32GB run Gemma 4 E2B?
Yes, RTX 5090 32GB can run Gemma 4 E2B with a B grade (Runs well). Expected decode speed: 96.9 tok/s.
How much VRAM does Gemma 4 E2B need?
Gemma 4 E2B (5.099999904632568B parameters) requires approximately 7.7 GB of memory with Q4_K_M quantization.
What is the best quantization for Gemma 4 E2B?
The recommended quantization for Gemma 4 E2B is Q4_K_M, which balances quality and memory efficiency.
What speed will Gemma 4 E2B run at on RTX 5090 32GB?
On RTX 5090 32GB, Gemma 4 E2B achieves approximately 96.9 tokens per second decode speed with a time-to-first-token of 1998ms using Q4_K_M quantization.
Can RTX 5090 32GB run Gemma 4 E2B for coding?
For coding workloads, Gemma 4 E2B on RTX 5090 32GB receives a B grade with 96.9 tok/s and 128K context.
What context window can Gemma 4 E2B use on RTX 5090 32GB?
On RTX 5090 32GB, Gemma 4 E2B can safely use up to 128K tokens of context. The model's official context limit is 128K, 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/gemma-4-e2b-on-rtx-5090-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: