RX 7900 XT 20GBGünstige Wahl
20 GB VRAM (+4)800 GB/s (+160)
C
Adds memory headroom for longer context windows and future model growth.52.5 tok/s Dekodierung
Adds memory headroom for longer context windows and future model growth.
ca. $899 MSRP
Can starcoder2 15b i1 run on RX 9070 16GB?
YES — Tight Fit
C51Usable
Estimated from fit model
starcoder2 15b i1 needs ~13.4 GB VRAM. RX 9070 16GB has 16.0 GB. With Q4_K_M quantization, expect ~43 tok/s.
Runtime: llama.cppCapacity: TightBandwidth: MediumStack: 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) — 13.4 GB, 43.4 tok/s, Tight fit
13.4 GB required16.0 GB available
84% VRAM used
Fit status
Tight fit
Decode
43.4 tok/s
TTFT
4464 ms
Safe context
40K
Memory
13.4 GB / 16.0 GB
Memory breakdown
Weights9.2 GB
KV Cache1.8 GB
Runtime0.9 GB
Headroom1.6 GB
See how fast it feels
See how fast it feelsstarcoder2 15b i1 on RX 9070 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: 43.4 tok/s decode · 4.5s TTFT (warm) · 108 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 | 43.4 tok/s | 2435 ms | 40K |
| Coding | C | Tight fit | 43.4 tok/s | 4464 ms | 40K |
| Agentic Coding | C | Tight fit | 43.4 tok/s | 6494 ms | 40K |
| Reasoning | C | Tight fit | 43.4 tok/s | 5276 ms | 40K |
| RAG | C | Tight fit | 43.4 tok/s | 8117 ms | 40K |
Inference speed
starcoder2 15b i1 inference speed — tokens per second by GPU & Mac
Estimated decode speed (tokens/sec) for starcoder2 15b i1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~131 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 | Q4_K_M | 131.2 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 83.7 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 75.5 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 71.6 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 68.3 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 60.9 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 50.7 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 48.1 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 34.7 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 34.7 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 26.7 | Heavy offload |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 26.2 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 24.0 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 21.2 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 15.7 | Heavy offload |
| RTX 4060 8GB | 8 GB | Q4_K_M | 5.9 | Too big |
Estimates for single-stream decoding at Q4_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 i1 (15B params) fits at each quantization level on RX 9070 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C49 |
Q3_K_S | 3 | 7.4 GB | Low | C51 |
NVFP4 | 4 | 8.4 GB | Medium | C51 |
Q4_K_M | 4 | 9.2 GB | Medium | C51 |
Q5_K_M | 5 | 10.8 GB | High | C51 |
Q6_KBest for your GPU | 6 | 12.3 GB | High | C50 |
Q8_0 | 8 | 16.1 GB | Very High | F0 |
F16 | 16 | 30.7 GB | Maximum | F0 |
Get started
Copy-paste commands to run starcoder2 15b i1 on your machine.
Run
lms load hf-mradermacher--starcoder2-15b-i1-gguf && lms server startUpgrade-Optionen
Hardware, die starcoder2 15b i1 gut ausführt
RX 7900 XTX 24GBBestes Preis-Leistungs-Verhältnis
24 GB VRAM (+8)960 GB/s (+320)
C
Raises estimated decode speed by about 74%.75.5 tok/s Dekodierung
Raises estimated decode speed by about 74%.
Adds memory headroom for longer context windows and future model growth.
ca. $999 MSRP
AMD Instinct MI100 32GBAMD-Upgrade
32 GB VRAM (+16)1228 GB/s (+588)
C
Raises estimated decode speed by about 101%.87.2 tok/s Dekodierung
Raises estimated decode speed by about 101%.
Adds memory headroom for longer context windows and future model growth.
ca. $11,500 MSRP
Frequently asked questions
Can RX 9070 16GB run starcoder2 15b i1?
Yes, RX 9070 16GB can run starcoder2 15b i1 with a C grade (Tight fit). Expected decode speed: 43.4 tok/s.
How much VRAM does starcoder2 15b i1 need?
starcoder2 15b i1 (15B parameters) requires approximately 13.4 GB of memory with Q4_K_M quantization.
What is the best quantization for starcoder2 15b i1?
The recommended quantization for starcoder2 15b i1 is Q4_K_M, which balances quality and memory efficiency.
What speed will starcoder2 15b i1 run at on RX 9070 16GB?
On RX 9070 16GB, starcoder2 15b i1 achieves approximately 43.4 tokens per second decode speed with a time-to-first-token of 4464ms using Q4_K_M quantization.
Can RX 9070 16GB run starcoder2 15b i1 for coding?
For coding workloads, starcoder2 15b i1 on RX 9070 16GB receives a C grade with 43.4 tok/s and 40K context.
What context window can starcoder2 15b i1 use on RX 9070 16GB?
On RX 9070 16GB, starcoder2 15b i1 can safely use up to 40K tokens of context. The model's official context limit is —, 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/hf-mradermacher--starcoder2-15b-i1-gguf-on-rx-9070-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: