OpenCoder 1.5B Base — Hardware Requirements & GPU Compatibility
ChatCode
OpenCoder 1.5B Base is a 1.9B-parameter open language model from infly. It supports a context window of up to 4,096 tokens. At BF16 it needs about 4.55 GB of VRAM — see which GPUs and Macs can run it below.
2.3K downloads
25 likesSpecifications
- Publisher
- infly
- Parameters
- 1.9B
- Architecture
- LlamaForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 96,640
- Release Date
- 2024-11-11
- License
- Other
Get Started
HuggingFace
How Much VRAM Does OpenCoder 1.5B Base Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 4.5 GB | 5.0 GB | 3.81 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run OpenCoder 1.5B Base?
BF16 · 4.5 GBOpenCoder 1.5B Base (BF16) requires 4.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 6+ GB is recommended. Using the full 4K context window can add up to 0.4 GB, bringing total usage to 5.0 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run OpenCoder 1.5B Base?
BF16 · 4.5 GB33 devices with unified memory can run OpenCoder 1.5B Base, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Derivatives (1)
Frequently Asked Questions
- How much VRAM does OpenCoder 1.5B Base need?
OpenCoder 1.5B Base requires 4.5 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.9B × 16 bits ÷ 8 = 3.8 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1.2 GB (at full 4K context)
VRAM usage by quantization
BF164.5 GBBF16 + full context5.0 GB- Can I run OpenCoder 1.5B Base on a Mac?
OpenCoder 1.5B Base requires at least 4.5 GB at BF16, 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 OpenCoder 1.5B Base locally?
Yes — OpenCoder 1.5B Base can run locally on consumer hardware. At BF16 quantization it needs 4.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is OpenCoder 1.5B Base?
At BF16, OpenCoder 1.5B Base can reach ~641 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~144 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 ÷ 4.5 × 0.55 = ~641 tok/s
Estimated speed at BF16 (4.5 GB)
~641 tok/s~144 tok/s~479 tok/s~396 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of OpenCoder 1.5B Base?
At BF16, the download is about 3.81 GB.
- Which GPUs can run OpenCoder 1.5B Base?
35 consumer GPUs can run OpenCoder 1.5B Base at BF16 (4.5 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 OpenCoder 1.5B Base?
33 devices with unified memory can run OpenCoder 1.5B Base at BF16 (4.5 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.