Beam 1.0 501B-A23B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
501.3B total, 23.4B active, 52 layers (3 dense and 49 MoE) with gated GQA attention and a 1M-token context. Text in, text out, Apache-2.0. Weights ship in BF16, FP8 and NVFP4; community GGUFs exist. Datacentre-scale to self-host.
Beam 1.0 501B-A23B needs about 303 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 165.6 GB | — | Too big | |
| Q3_K_M 3.41 bpw | 214.5 GB | — | Too big | |
| Q4_K_M 4.83 bpw | 303.5 GB | — | Too big | |
| Q5_K_M 5.67 bpw | 356.1 GB | — | Too big | |
| Q6_K 6.56 bpw | 411.9 GB | — | Too big | |
| Q8_0 8.50 bpw | 533.4 GB | — | Too big | |
| F16 16.00 bpw | 1003.4 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Beam 1.0 501B-A23B VRAM calculator →
Get Beam 1.0 501B-A23B running
The cheapest catalogued GPU that runs Beam 1.0 501B-A23B is the Apple M3 Ultra (512 GB).
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Beam 1.0 501B-A23B
No local Ollama tag. Ollama lists Beam only as a cloud-hosted 'beam:cloud' tag, which runs on Ollama's servers, not your machine.
Specifications
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- Parameters
- 501 Billion (23B active)
- Context window
- 1,000,000
- Architecture
- Mixture-of-Experts (3 dense + 49 MoE layers), gated GQA
- Provider
- Reflection AI
- Licence
- Apache-2.0
- Availability
- Weights downloadable
- Practical deployment
- Workstation (large unified memory or pro GPU)
- Specified at
- Q4_K_M
- System RAM
- 512 GB
- Record updated
- 2026-10-25
- Runs with
- Ollama: not supported source
Commercial use permitted. No usage restrictions beyond attribution.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Beam 1.0 501B-A23B — frequently asked questions
How much VRAM does Beam 1.0 501B-A23B need?
About 303 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Beam 1.0 501B-A23B run on an RTX 4090 (24 GB)?
No. Beam 1.0 501B-A23B needs about 303 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Beam 1.0 501B-A23B locally?
No local Ollama tag. Ollama lists Beam only as a cloud-hosted 'beam:cloud' tag, which runs on Ollama's servers, not your machine. Running the published tag would send your prompts to a hosted GPU rather than your own machine.