StarCoder 15B needs ~29.8 GB VRAM. AMD Instinct MI60 32GB has 32.0 GB. With Q5_K_M quantization, expect ~47 tok/s.
Operating mode
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
Fit status
Tight fit
Decode
47.4 tok/s
TTFT
4085 ms
Safe context
8K
Memory
29.8 GB / 32.0 GB
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.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 47.4 tok/s | 2228 ms | 8K |
| Coding | A | Tight fit | 47.4 tok/s | 4085 ms | 8K |
| Agentic Coding | F | Too heavy | 17.8 tok/s | 15860 ms | 8K |
| Reasoning | A | Tight fit | 47.4 tok/s | 4828 ms | 8K |
| RAG | F | Too heavy | 17.8 tok/s | 19824 ms | 8K |
How StarCoder 15B (15B params) fits at each quantization level on AMD Instinct MI60 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | B69 |
Q3_K_S | 3 | 7.4 GB | Low | B70 |
NVFP4 | 4 |
Copy-paste commands to run StarCoder 15B on your machine.
Run
lms load starcoder && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 30.5B | S | 75.9 tok/s | ||
| 27B | S | 32.9 tok/s |
Yes, AMD Instinct MI60 32GB can run StarCoder 15B with a A grade (Tight fit). Expected decode speed: 47.4 tok/s.
StarCoder 15B (15B parameters) requires approximately 29.8 GB of memory with Q5_K_M quantization.
The recommended quantization for StarCoder 15B is Q5_K_M, which balances quality and memory efficiency.
On AMD Instinct MI60 32GB, StarCoder 15B achieves approximately 47.4 tokens per second decode speed with a time-to-first-token of 4085ms using Q5_K_M quantization.
For coding workloads, StarCoder 15B on AMD Instinct MI60 32GB receives a A grade with 47.4 tok/s and 8K context.
On AMD Instinct MI60 32GB, StarCoder 15B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/starcoder-15b-on-instinct-mi60-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| Medium |
| A70 |
Q4_K_M | 4 | 9.2 GB | Medium | A71 |
Q5_K_M | 5 | 10.8 GB | High | A71 |
Q6_K | 6 | 12.3 GB | High | A72 |
Q8_0Best for your GPU | 8 | 16.1 GB | Very High | A74 |
F16 | 16 | 30.7 GB | Maximum | F0 |
| 27B | S | 33 tok/s |
| 35B | S | 63.8 tok/s |
| 30B | S | 78.5 tok/s |
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.