How much VRAM does StarCoder 2 15B need?

StarCoder 2 15B requires 10.7 GB VRAM at recommended quality (Q5_K_M). At lower quality settings, it can fit in as little as 7.3 GB.

What is the best GPU for StarCoder 2 15B?

The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for StarCoder 2 15B, achieving 210 tok/s at Q8_0 with an excellent rating.

Can I run StarCoder 2 15B on an RTX 4060 Ti?

Yes. On the NVIDIA GeForce RTX 4060 Ti 16GB, StarCoder 2 15B runs at 25 tok/s (Q5_K_M, good).

What quantization should I use for StarCoder 2 15B?

For the best quality, use Q5_K_M (10.7 GB VRAM). If your GPU has limited VRAM, Q3_K_M (7.3 GB) is the most efficient option with acceptable quality.

Is StarCoder 2 15B good for coding?

Yes. StarCoder 2 15B is used with Continue, LM Studio for local AI coding. For the best coding experience, pair it with an embedding model for local RAG.

CodingAI coding15.5B

Coding

StarCoder 2 15B

StarCoder · BigCode OpenRAIL-M

Trained on The Stack v2 with 619 programming languages. Full fill-in-the-middle (FIM) support for code completion. BigCode's best model, competitive but surpassed by Qwen 2.5 Coder on most benchmarks.

Parameters: 15.5B
Architecture: Dense
Context: 16,384 tokens
Released: 2024-02-28
Engines: llama.cpp, ollama, vLLM
Builder Tools: Continue, LM Studio

Parameters

15.5B

VRAM

10.7 GB

Context

16K

Formats

GPUs

StarCoder 2 15B (15.5B) requires 10.7 GB VRAM at recommended quality (Q5_K_M). At efficient quality (Q4_K_M), it fits in 9 GB VRAM, making it compatible with the NVIDIA RTX 4060 Laptop (40-60W). On NVIDIA Grace Blackwell Ultra GB300, expect approximately 210 tok/s at Q8_0. For the best experience, Starter AI Desktop ($582) is recommended.

Source: OwnRig methodology

VRAM (Recommended)

10.7 GB

Quantization

Q5_K_M

File Size

9.3 GB

Max Context

16K tokens

Primary Use

Coding

Memory

VRAM Requirements

Quality	Quantization	VRAM	File Size
full	Q8_0	16.8 GB	15.5 GB
recommended	Q5_K_M	10.7 GB	9.3 GB
efficient	Q4_K_M	9 GB	7.8 GB
compressed	Q3_K_M	7.3 GB	6 GB

Scaling

Context Length Impact

KV cache VRAM at Q5_K_M quality. Longer context = more memory.

Context	KV Cache	Total VRAM
2K	205 MB	10.9 GB
4K	410 MB	11.1 GB
8K	819 MB	11.5 GB
16K	1.5 GB	12.2 GB

Compatible GPUs

21 devices


NVIDIA Grace Blackwell Ultra GB300	Q8_0	210 tok/s	Excellent
NVIDIA GeForce RTX 4090	Q8_0	50 tok/s	Excellent
AMD Radeon Pro W7900	Q8_0	54 tok/s	Excellent
NVIDIA GeForce RTX 4060 Ti 16GB	Q5_K_M	25 tok/s	Good
AMD Radeon RX 7900 XTX	Q8_0	43 tok/s	Good
NVIDIA RTX PRO 6000 Blackwell	Q8_0	63 tok/s	Good
NVIDIA RTX PRO 6000 Blackwell Max-Q	Q8_0	58 tok/s	Good
AMD Radeon RX 9070	Q5_K_M	44 tok/s	Good
NVIDIA GeForce RTX 5060 Ti 16GB	Q5_K_M	28 tok/s	Good
NVIDIA GeForce RTX 3080 10GB	Q3_K_M	22 tok/s	Acceptable
NVIDIA RTX 4060 Laptop (40-60W)	Q3_K_M	10 tok/s	Acceptable
NVIDIA RTX 4070 Laptop (80-115W)	Q3_K_M	11 tok/s	Acceptable
NVIDIA GeForce RTX 4070 Ti 12GB	Q3_K_M	28 tok/s	Acceptable
NVIDIA RTX 4080 Laptop (120-150W)	Q3_K_M	20 tok/s	Acceptable
NVIDIA RTX 4090 Laptop (150-175W)	Q5_K_M	21 tok/s	Acceptable
AMD Radeon RX 9060 XT 16GB	Q5_K_M	22 tok/s	Acceptable
Apple M3 Pro (18GB Unified)	Q3_K_M	4 tok/s	Marginal
NVIDIA GeForce RTX 4060 8GB	Q3_K_M	16 tok/s	Marginal
AMD Radeon RX 7600	Q3_K_M	4 tok/s	Marginal
NVIDIA GeForce RTX 5060 8GB	Q3_K_M	18 tok/s	Marginal
AMD Radeon RX 9060 XT 8GB	Q5_K_M	–	Not viable

Showing 21 of 21 entries

Builder Context

StarCoder 2 15B is commonly used with Continue, LM Studio. For an AI coding workflow, pair it with an embedding model like nomic-embed-text for local RAG.

FAQ

Frequently Asked Questions

How much VRAM does StarCoder 2 15B need?: StarCoder 2 15B requires 10.7 GB VRAM at recommended quality (Q5_K_M). At lower quality settings, it can fit in as little as 7.3 GB.
What is the best GPU for StarCoder 2 15B?: The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for StarCoder 2 15B, achieving 210 tok/s at Q8_0 with an excellent rating.
Can I run StarCoder 2 15B on an RTX 4060 Ti?: Yes. On the NVIDIA GeForce RTX 4060 Ti 16GB, StarCoder 2 15B runs at 25 tok/s (Q5_K_M, good).
What quantization should I use for StarCoder 2 15B?: For the best quality, use Q5_K_M (10.7 GB VRAM). If your GPU has limited VRAM, Q3_K_M (7.3 GB) is the most efficient option with acceptable quality.
Is StarCoder 2 15B good for coding?: Yes. StarCoder 2 15B is used with Continue, LM Studio for local AI coding. For the best coding experience, pair it with an embedding model for local RAG.

All models

Data confidence: verified. Source

VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.StarCoder is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.