Beam-1.0-501B-A23B needs about 167.1 GB of memory at IQ2_M (a 164.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 133.8 GB (IQ2_XXS) to 197.1 GB (IQ3_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 7.0 GB.
Beam 1.0 501B-A23B: a 501B‑parameter MoE model for token‑efficient reasoning and coding
Beam 1.0 501B-A23B is a 501.3B‑parameter sparse mixture‑of‑experts model with 23.4B active parameters. It supports a 1M token context window and is optimized for English text. The model excels in reasoning, coding, and agentic tool use.
Good at
- Token‑efficient reasoning
- Software engineering and code generation
- Agentic tool integration
Limits
- Requires large VRAM for full context
- No vision or audio modalities
- Apache‑2.0 license restricts commercial use without attribution
Best for
- Long‑form reasoning tasks
- GitHub issue resolution
- Agentic workflow automation
Who it’s for. Developers and researchers needing high‑quality reasoning and coding support in a local LLM. The model is suitable for CLI and DevOps environments that can accommodate its memory demands.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 133.8 GB (3 parts) | 136.0 GB | Too big | Get file → | |
| IQ2_M | 164.8 GB (4 parts) | 167.1 GB | Too big | Get file → | |
| Q2_K | 186.8 GB (5 parts) | 189.1 GB | Too big | Get file → | |
| IQ3_XXS | 197.1 GB (5 parts) | 199.4 GB | Too big | Get file → |
For 160‑GB systems, use IQ2_XXS (133.79 GB, 136 GB memory at 8 k context). For 256‑GB systems, IQ3_XXS (197.11 GB, 199.4 GB memory at 8 k context) is recommended. Smaller budgets may use IQ2_M or Q2_K, but memory will be higher.
What GPU do you need for Beam-1.0-501B-A23B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Beam-1.0-501B-A23B quant should you choose?
IQ2_M (164.8 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is IQ2_XXS at 133.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Beam-1.0-501B-A23B
How much VRAM does Beam-1.0-501B-A23B need?
About 167.1 GB at IQ2_M with an 8K context window. That is the 164.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Beam-1.0-501B-A23B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 136.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Beam-1.0-501B-A23B GGUF?
It depends on the quant: IQ2_XXS is 133.8 GB, IQ2_M is 164.8 GB, Q2_K is 186.8 GB, IQ3_XXS is 197.1 GB.
What context length does Beam-1.0-501B-A23B support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 1.7 GB at 8K and 7.0 GB at 32K.
Where can I download Beam-1.0-501B-A23B GGUF?
The files are on Hugging Face in the AtomicChat/Beam-1.0-501B-A23B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Beam-1.0-501B-A23B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Beam 1.0 501B-A23B on 8 GB VRAM?
No. The smallest quant requires 136 GB memory at 8 k context, far exceeding 8 GB VRAM.
Does Beam support image input?
No. The model only supports text modalities.
What license applies to this model?
Apache‑2.0. Commercial use requires attribution and compliance with the license terms.