StarCoder 15B needs ~36.2 GB VRAM. RTX PRO 6000 Blackwell Workstation Edition 96GB has 96.0 GB. With Q5_K_M quantization, expect ~142 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
Runs well
Decode
142.2 tok/s
TTFT
1362 ms
Safe context
8K
Memory
36.2 GB / 96.0 GB
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 142.2 tok/s | 743 ms | 8K |
| Coding | A | Runs well | 142.2 tok/s | 1362 ms | 8K |
| Agentic Coding | A | Runs well | 142.2 tok/s | 1981 ms | 8K |
| Reasoning | A | Runs well | 142.2 tok/s | 1609 ms | 8K |
| RAG | A | Runs well | 142.2 tok/s | 2476 ms | 8K |
Inference speed
Estimated decode speed (tokens/sec) for StarCoder 15B at Q5_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~113 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 | Q5_K_M | 113.4 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q5_K_M | 52.6 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q5_K_M | 43.8 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q5_K_M | 41.6 | Fits |
| RTX 4090 24GB | 24 GB | Q5_K_M | 36.3 | Too big |
RX 7900 XTX 24GB | 24 GB | Q5_K_M | 32.8 | Too big |
| RTX 3090 24GB | 24 GB | Q5_K_M | 31.1 | Too big |
MacBook Pro M4 Max 128GB | 128 GB | Q5_K_M | 30.0 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q5_K_M | 30.0 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q5_K_M | 22.7 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q5_K_M | 20.8 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q5_K_M | 18.3 | Tight |
| RTX 4080 Super 16GB | 16 GB | Q5_K_M | 13.1 | Too big |
| RTX 4070 12GB | 12 GB | Q5_K_M | 5.4 | Too big |
| RTX 3060 12GB | 12 GB | Q5_K_M | 3.4 | Too big |
| RTX 4060 8GB | 8 GB | Q5_K_M | 2.8 | Too big |
Estimates for single-stream decoding at Q5_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.
How StarCoder 15B (15B params) fits at each quantization level on RTX PRO 6000 Blackwell Workstation Edition 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | B64 |
Q3_K_S | 3 | 7.4 GB | Low | B64 |
NVFP4 | 4 | 8.4 GB | Medium | B64 |
Q4_K_M | 4 | 9.2 GB | Medium | B64 |
Q5_K_M | 5 | 10.8 GB | High | B65 |
Q6_K | 6 | 12.3 GB | High | B65 |
Q8_0 | 8 | 16.1 GB | Very High | B65 |
F16Best for your GPU | 16 | 30.7 GB | Maximum | B67 |
Copy-paste commands to run StarCoder 15B on your machine.
Run
lms load starcoder && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Devstral 2 123B Instruct | 123B | S | 21.8 tok/s | |
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 227.6 tok/s | |
| Qwen 3.5 27B | 27B | S | 98.7 tok/s | |
| Qwen 3.6 27B | 27B | S | 99 tok/s | |
| Qwen 3.5 122B A10B | 122B | S | 60.5 tok/s |
Yes, RTX PRO 6000 Blackwell Workstation Edition 96GB can run StarCoder 15B with a A grade (Runs well). Expected decode speed: 142.2 tok/s.
StarCoder 15B (15B parameters) requires approximately 36.2 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 RTX PRO 6000 Blackwell Workstation Edition 96GB, StarCoder 15B achieves approximately 142.2 tokens per second decode speed with a time-to-first-token of 1362ms using Q5_K_M quantization.
For coding workloads, StarCoder 15B on RTX PRO 6000 Blackwell Workstation Edition 96GB receives a A grade with 142.2 tok/s and 8K context.
On RTX PRO 6000 Blackwell Workstation Edition 96GB, 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-rtx-pro-6000-blackwell-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: