StarCoder2 3B GGUF — Hardware Requirements & GPU Compatibility
ChatCode
StarCoder2 3B GGUF is a 3B-parameter open language model from second-state in the StarCoder family. It supports a context window of up to 16,384 tokens. At Q4_K_M it needs about 2.16 GB of VRAM — see which GPUs and Macs can run it below.
3.2K downloads
16 likesSpecifications
- Publisher
- second-state
- Family
- StarCoder
- Parameters
- 3B
- Architecture
- Starcoder2ForCausalLM
- Context Length
- 16,384 tokens
- Vocabulary Size
- 49,152
- Release Date
- 2024-03-20
- License
- bigcode-openrail-m
Get Started
HuggingFace
How Much VRAM Does StarCoder2 3B GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 1.6 GB | 2.1 GB | 1.27 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 1.7 GB | 2.1 GB | 1.31 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 1.8 GB | 2.3 GB | 1.46 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 1.9 GB | 2.3 GB | 1.50 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 2.2 GB | 2.6 GB | 1.80 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 2.5 GB | 2.9 GB | 2.14 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 2.8 GB | 3.3 GB | 2.48 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 3.4 GB | 3.8 GB | 3.00 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run StarCoder2 3B GGUF?
Q4_K_M · 2.2 GBStarCoder2 3B GGUF (Q4_K_M) requires 2.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 16K context window can add up to 0.4 GB, bringing total usage to 2.6 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run StarCoder2 3B GGUF?
Q4_K_M · 2.2 GB33 devices with unified memory can run StarCoder2 3B GGUF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does StarCoder2 3B GGUF need?
StarCoder2 3B GGUF requires 2.2 GB of VRAM at Q4_K_M, or 3.4 GB at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 3B × 4.8 bits ÷ 8 = 1.8 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 0.8 GB (at full 16K context)
VRAM usage by quantization
Q4_K_M2.2 GBQ4_K_M + full context2.6 GB- What's the best quantization for StarCoder2 3B GGUF?
For StarCoder2 3B GGUF, Q4_K_M (2.2 GB) offers the best balance of quality and VRAM usage. Q5_0 (2.2 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.6 GB.
VRAM requirement by quantization
Q2_K1.6 GBQ4_01.9 GBQ4_K_M ★2.2 GBQ5_02.2 GBQ5_K_S2.4 GBQ8_03.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run StarCoder2 3B GGUF on a Mac?
StarCoder2 3B GGUF requires at least 1.6 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run StarCoder2 3B GGUF locally?
Yes — StarCoder2 3B GGUF can run locally on consumer hardware. At Q4_K_M quantization it needs 2.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is StarCoder2 3B GGUF?
At Q4_K_M, StarCoder2 3B GGUF can reach ~1350 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~303 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 2.2 × 0.55 = ~1350 tok/s
Estimated speed at Q4_K_M (2.2 GB)
~1350 tok/s~303 tok/s~1009 tok/s~834 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of StarCoder2 3B GGUF?
At Q4_K_M, the download is about 1.80 GB. The full-precision Q8_0 version is 3.00 GB. The smallest option (Q2_K) is 1.27 GB.
- Which GPUs can run StarCoder2 3B GGUF?
35 consumer GPUs can run StarCoder2 3B GGUF at Q4_K_M (2.2 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run StarCoder2 3B GGUF?
33 devices with unified memory can run StarCoder2 3B GGUF at Q4_K_M (2.2 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.