Model

Beam 1.0 (501B-A23B)

Made by Reflection · License: Apache 2.0

A big model for chat and code. It runs on Ollama’s servers, not on your computer.

Will it run on my computer?

Yes. It runs on Ollama’s servers, so you only need Ollama and an internet connection. Nothing downloads.

Start it

Install Ollama from ollama.com/download.
Sign in to Ollama.
Open Terminal.
Paste this command:

ollama run beam:cloud

What happens next

Nothing downloads. Type your message and press Enter.
Type /bye to stop.

If it breaks

The :cloud command fails or asks you to sign in.
Cloud models run on Ollama's servers, so Ollama needs your account before it will run them.
Sign in once, then run the command again.
```
ollama signin
```
Source: 1 · 2

Sizes and versions

Could I run it myself?

For the UD-IQ1_S file (103.1 GB download).

64 GB+ Mac	Won't fit
32 GB graphics card	Won't fit
AMD Ryzen AI Max+ PC, 128 GB (graphics memory set to 96 GB)	Won't fit
128 GB Mac	Won't fit
256 GB Mac	Fits
512 GB Mac	Fits

This is our estimate from published download sizes. We did not test these ourselves.
Fits = download x 1.25 + 2 GB fits in usable memory. That leaves room for longer chats.
Tight = only download + 1.5 GB fits. Short chats work, but long chats or documents may spill onto the CPU and slow down.
Usable memory on a graphics card is all of its graphics memory.
On a Mac it is 2/3 of memory up to 32 GB and 3/4 at 64 GB+. By default macOS keeps part of memory away from the GPU. Apple says a 32 GB Mac gives the GPU 21 GB and a 64 GB Mac 48 GB.
On an AMD Ryzen AI Max+ PC with 128 GB, it is the graphics memory you set in AMD Software. AMD says you can set up to 96 GB.
Apple · AMD

START HERE Cloud only (no easy local)

STEP 1Install Ollama from ollama.com/download, open it and sign in (cloud models need a free Ollama account; heavy use is paid).

STEP 2Paste the command below in Terminal or PowerShell.

RUN

ollama run beam:cloud

SIZENothing to download: it runs on Ollama's servers, not your computer

NEEDSAn internet connection and an Ollama account. Running it yourself needs 192 GB+ of memory (smallest file is 103 GB).

NOTEYour chats go to Ollama's servers. LM Studio also offers it as a paid cloud model only.

ADVANCEDWant it on your own machine? llama.cpp with the smallest Unsloth file. Minimum llama.cpp build not pinned as of Oct 19, so use the newest.

llama-server -hf unsloth/Beam-1.0-501B-A23B-GGUF:UD-IQ1_S --jinja

SOURCEsource · checked 2026-10-19

Recommended quants

Official NVFP4 (~294 GB)
reflection/Beam-1.0-501B-A23B-NVFP4
The practical serving choice on Blackwell (4x B200, 2x B300, or 8x RTX Pro 6000 per the HF launch post).
Official FP8 (~503 GB)
reflection/Beam-1.0-501B-A23B-FP8
For Hopper and older GPUs, for example 8x H200.
Unsloth UD-IQ1_S (103.1 GB) / UD-IQ2_XXS (133.9 GB) / UD-Q2_K_XL (186.9 GB)
unsloth/Beam-1.0-501B-A23B-GGUF
Low-bit options for 192-256 GB Macs and bigger; quality loss unmeasured here.
Unsloth UD-Q4_K_XL (306.5 GB) / Q8_0 (532.8 GB)
unsloth/Beam-1.0-501B-A23B-GGUF
Big Mac Studio pairs or multi-GPU servers.
DFlash2 drafter
reflection/Beam-1.0-501B-A23B-DFlash2
Speculative-decoding draft model; recommended in the official SGLang recipe.

Scores and how it compares

Independent score: Artificial Analysis Intelligence Index 30, checked 2026-10-19 · source.

Arena: not on the Arena boards we use (checked 2026-10-19).

Pick this if you want Reflection's Beam and are fine with your chats going to Ollama's servers. Artificial Analysis scores it 30, among the highest-scoring open models we track.

Skip this if you want everything to stay on your own computer. It is far too big for a home PC, so pick your computer to see the top-ranked model that fits yours.

Compare: Qwen3.8-27B · Pick your computer

BEST PICK ONNot the top pick on any computer page right now.

Settings and apps

Chat template Works

Modified Harmony format. The response template ships in the tokenizer, so transformers' parse_response splits reasoning, answer and tool calls for you. Set reasoning_effort to low, medium (default), high, xhigh or max. preserve_thinking keeps reasoning across turns. Tool-call arguments use Beam's own XML-style grammar.

Fix: Needs transformers >= 5.20.1. On SGLang pass --tool-call-parser beam --reasoning-parser beam, or tool calls and reasoning come back as raw text. When parsing tool calls in transformers, pass tools to parse_response too so arguments get cast to their declared types.

Sampling settings

Official (generation_config.json)	`temp 0.7, top_p 0.99, repetition_penalty 1.0`
Reasoning effort	`medium by default; raise to high for hard coding or long-context retrieval (HF's vibe tests saw low effort miss steps)`

Runtimes

vLLM	Works	Day-0 support. BF16 needs 16 GPUs (2x 8x H200): vllm serve reflection/Beam-1.0-501B-A23B --tensor-parallel-size 16. Optional DFlash speculative config.
SGLang	Works	Day-0 support. NVFP4 on 4x B300 (trtllm_mha) or FP8 on 8x H200 (fa3), with DFLASH speculative decoding and beam parsers.
llama.cpp	Caveats	Unsloth GGUFs published on launch day (UD-IQ1_S ~103 GB up); minimum llama.cpp build not pinned as of Oct 19.
Ollama	Caveats	Library page beam exists; only :cloud tag as of Oct 19 — not a local download.
LM Studio	Unverified	No local listing confirmed as of Oct 19.
MLX	Unverified	No mlx-community Beam quant confirmed as of Oct 19.

Tool calling in agent tools

Claude Code (local endpoint)	Caveats	Ollama documents `ollama launch claude --model beam:cloud` (hosted). Local OpenAI-compatible endpoint behavior not verified.
OpenCode	Caveats	Ollama documents `ollama launch opencode --model beam:cloud` (hosted).

Sources

MADE BYReflection

LICENSEApache 2.0 · model page · checked 2026-10-19

RELEASED2026-10-16

CHECKED2026-10-19 · 5 sources

Reflection's big open coding model. Too large for a home PC—try it through Ollama Cloud. Claims shorter answers than similar open models.

Known issues

Sources checked

Spotted something wrong or a new fix? Email corrections to [email protected]. Corrections are reviewed before publishing.