Starcoder2 15B Instruct v0.1 — Hardware Requirements & GPU Compatibility
ChatCode
Starcoder2 15B Instruct v0.1 is a 16.0B-parameter open language model from BigCode in the StarCoder family. It supports a context window of up to 16,384 tokens. At BF16 it needs about 32.38 GB of VRAM — see which GPUs and Macs can run it below.
Starcoder2 15B Instruct v0.1 runs on a 36 GB+ Mac or a workstation GPU
Best local pick → Mac Studio M5 Max (36 GB) · BF16 · 33.6 GB · ~10 tok/s
Macs from 36 GB (BF16 · ~10 tok/s)
bigcode-openrail-m
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Starcoder2 15B Instruct v0.1
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve bigcode/starcoder2-15b-instruct-v0.1 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX A6000 (48 GB) (14 GB headroom) · BF16
- Generation speed
- ~15 tok/s
- generation speed
- Cost per 1M output tokens
- $5.95
- per 1M output tokens
How Much VRAM Does Starcoder2 15B Instruct v0.1 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 32.4 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 33.6 GB |
Selected BF16
Brain floating point 1633.6GBat 16K context
- Weights
- 31.9 GB
- KV cache
- 1.3 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 9.5 GB more
Which Hardware Can Run Starcoder2 15B Instruct v0.1?
BF16 · 32.4 GBStarcoder2 15B Instruct v0.1 (BF16) requires 32.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 43+ GB is recommended. Using the full 16K context window can add up to 1.2 GB, bringing total usage to 33.6 GB. No consumer GPU has enough memory. 77 devices with unified memory can run Starcoder2 15B Instruct v0.1, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M5 Max (48 GB).
48 GB
48 GB tier →fits · 14.4 GB free · up to 16K ctx
2 Mac classes · 1 device family
M5 Max48 GB~13Simulate output on Mac Studio M5 Max (48 GB)M5 Pro48 GB~7Simulate output on Mac Mini M5 Pro (48 GB)Snapdragon X2 Elite Extreme (X2E-96-100)~5Simulate output on Snapdragon X2 Elite Extreme Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to Starcoder2 15B Instruct v0.1
StarCoder family · 5 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Apriel 1.6 15B ThinkerServiceNow-AI | — | 13.2 GB | ~67 | same size |
| Kimi VL A3B InstructMoonshot AI | — | 10.7 GB | ~208 | same size |
| LLaDA2.1 MiniInclusion AI | — | 33.5 GB | —needs > 24 GB | same size |
| LLaDA2.0 MiniInclusion AI | — | 10.7 GB | ~406 | same size |
| Moonlight 16B A3BMoonshot AI | — | 10.1 GB | ~229 | same size |
| DeepSeek Coder v2 Lite BaseDeepSeek | — | 10.2 GB | ~243 | same size |
Specifications
- Publisher
- BigCode
- Family
- StarCoder
- Parameters
- 16.0B
- Architecture
- Starcoder2ForCausalLM
- Context Length
- 16,384 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2024-04-23
- License
- bigcode-openrail-m
Frequently Asked Questions
How much VRAM does Starcoder2 15B Instruct v0.1 need?
Starcoder2 15B Instruct v0.1 requires 32.4 GB of VRAM at BF16. Full 16K context adds up to 1.2 GB (33.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 16.0B × 16 bits ÷ 8 = 31.9 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 1.7 GB (at full 16K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Starcoder2 15B Instruct v0.1?
No — Starcoder2 15B Instruct v0.1 requires at least 32.4 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Starcoder2 15B Instruct v0.1 on a Mac?
Yes — Mac Studio M5 Max (36 GB) and 65 other Macs can run Starcoder2 15B Instruct v0.1. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 32.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run Starcoder2 15B Instruct v0.1 locally?
Yes — Starcoder2 15B Instruct v0.1 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Starcoder2 15B Instruct v0.1?
At BF16, Starcoder2 15B Instruct v0.1 can reach ~148 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 32.38 × 0.65 = ~161 tok/s
Estimated speed at BF16 (32.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Starcoder2 15B Instruct v0.1?
At BF16, the download is about 31.92 GB.
Which GPUs can run Starcoder2 15B Instruct v0.1?
No single consumer GPU has enough VRAM to run Starcoder2 15B Instruct v0.1 at BF16 (32.4 GB). Multi-GPU or professional hardware is required.
Which devices can run Starcoder2 15B Instruct v0.1?
77 devices with unified memory can run Starcoder2 15B Instruct v0.1 at BF16 (32.4 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.