Outmake Models
Models

Beam 1.0 501B A23B

reflection · October 2026

Get Hugging Face

A 501B, 23B active chat model from reflection.

Rating
4.8
Downloads
6.9K
Likes
18
Parameters
501B, 23B active
Context
1M
Licence
apache-2.0

Too big for this Mac

Its smallest size needs 126 GB of memory, more than M4 · 16 GB can give it.

Ratings

4.8 out of 5, across the tests below.

ScienceGPQA Diamond
90.6%
Expert questionsHumanity's Last Exam
51.1%
Software fixesSWE-bench Verified
81.6%
MathsAIME 2026
97.7%

GPQA Diamond: questions PhD scientists write for each other. Humanity's Last Exam: questions written to be beyond today's models. SWE-bench Verified: real GitHub issues fixed so the project's tests pass. AIME 2026: this year's AIME competition problems. Scores are the ones filed on the model's Hugging Face page or the board's own table, read 2026-11-05; some come from the maker.

Beam 1.0 501B A23B runs well from a Mac with an M2 Ultra and 192 GB of memory. 5 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From unsloth/Beam-1.0-501B-A23B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
UD-IQ1_S103 GB103 GBestimatedOpen
UD-IQ1_M124 GB124 GBestimatedOpen
UD-IQ2_XXS134 GB134 GBestimatedOpen
UD-IQ2_M165 GB165 GBestimatedOpen
UD-Q2_K_XL187 GB187 GBestimatedOpen
UD-IQ3_XXS197 GB197 GBestimatedOpen
UD-Q3_K_XL242 GB243 GBestimatedOpen
UD-Q4_K_XL307 GB307 GBestimatedOpen
UD-Q5_K_XL369 GB370 GBestimatedOpen
UD-Q6_K_XL453 GB453 GBestimatedOpen
Q8_0533 GB533 GBestimatedOpen
BF161003 GB1003 GBestimatedOpen

Run It Anywhere

Beam 1.0 501B A23B is an open model, so any app that runs GGUF files can run it. These take the UD-IQ1_S size from unsloth straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/unsloth/Beam-1.0-501B-A23B-GGUF:UD-IQ1_S
  • llama.cppMac, Windows, Linuxllama-server -hf unsloth/Beam-1.0-501B-A23B-GGUF:UD-IQ1_S
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/unsloth/Beam-1.0-501B-A23B-GGUF:UD-IQ1_S
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 165 GB
8 GBNone worth runningneeds 165 GB
10 GBNone worth runningneeds 165 GB
11 GBNone worth runningneeds 165 GB
12 GBNone worth runningneeds 165 GB
16 GBNone worth runningneeds 165 GB
20 GBNone worth runningneeds 165 GB
24 GBNone worth runningneeds 165 GB
32 GBNone worth runningneeds 165 GB
48 GBNone worth runningneeds 165 GB

The largest size, of those that keep three bits a weight or more, whose memory at an 8K chat is under 92% of the card's; the rest is the desktop's. Estimated from the files, the same way as for a Mac; speed on a PC is not estimated yet. A size that doesn't fit the card still runs, slower, with part of it in ordinary memory.

On every Mac
MacSizeFitMemoryWrites
M6 · 16 GBUD-IQ1_SToo big126 GB
M6 · 24 GBUD-IQ1_SToo big126 GB
M6 · 32 GBUD-IQ1_SToo big126 GB
M5 · 16 GBUD-IQ1_SToo big126 GB
M5 · 24 GBUD-IQ1_SToo big126 GB
M5 · 32 GBUD-IQ1_SToo big126 GB
M5 Pro · 24 GBUD-IQ1_SToo big126 GB
M5 Pro · 48 GBUD-IQ1_SToo big126 GB
M5 Pro · 64 GBUD-IQ1_SToo big126 GB
M5 Max · 36 GBUD-IQ1_SToo big126 GB
M5 Max · 48 GBUD-IQ1_SToo big126 GB
M5 Max · 64 GBUD-IQ1_SToo big126 GB
M5 Max · 128 GBUD-IQ1_SToo big126 GB
M5 Ultra · 96 GBUD-IQ1_SToo big126 GB
M5 Ultra · 256 GBUD-IQ3_XXSRuns well203 GB39
M5 Ultra · 512 GBUD-Q4_K_XLRuns great329 GB28
M4 · 16 GBUD-IQ1_SToo big126 GB
M4 · 24 GBUD-IQ1_SToo big126 GB
M4 · 32 GBUD-IQ1_SToo big126 GB
M4 Pro · 24 GBUD-IQ1_SToo big126 GB
M4 Pro · 48 GBUD-IQ1_SToo big126 GB
M4 Pro · 64 GBUD-IQ1_SToo big126 GB
M4 Max · 36 GBUD-IQ1_SToo big126 GB
M4 Max · 48 GBUD-IQ1_SToo big126 GB
M4 Max · 64 GBUD-IQ1_SToo big126 GB
M4 Max · 96 GBUD-IQ1_SToo big126 GB
M4 Max · 128 GBUD-IQ1_SToo big126 GB
M3 · 8 GBUD-IQ1_SToo big126 GB
M3 · 16 GBUD-IQ1_SToo big126 GB
M3 · 24 GBUD-IQ1_SToo big126 GB
M3 Pro · 18 GBUD-IQ1_SToo big126 GB
M3 Pro · 36 GBUD-IQ1_SToo big126 GB
M3 Max · 36 GBUD-IQ1_SToo big126 GB
M3 Max · 48 GBUD-IQ1_SToo big126 GB
M3 Max · 64 GBUD-IQ1_SToo big126 GB
M3 Max · 96 GBUD-IQ1_SToo big126 GB
M3 Max · 128 GBUD-IQ1_SToo big126 GB
M3 Ultra · 96 GBUD-IQ1_SToo big126 GB
M3 Ultra · 256 GBUD-IQ3_XXSRuns well203 GB22
M3 Ultra · 512 GBUD-Q4_K_XLRuns great329 GB16
M2 · 8 GBUD-IQ1_SToo big126 GB
M2 · 16 GBUD-IQ1_SToo big126 GB
M2 · 24 GBUD-IQ1_SToo big126 GB
M2 Pro · 16 GBUD-IQ1_SToo big126 GB
M2 Pro · 32 GBUD-IQ1_SToo big126 GB
M2 Max · 32 GBUD-IQ1_SToo big126 GB
M2 Max · 64 GBUD-IQ1_SToo big126 GB
M2 Max · 96 GBUD-IQ1_SToo big126 GB
M2 Ultra · 64 GBUD-IQ1_SToo big126 GB
M2 Ultra · 128 GBUD-IQ1_SToo big126 GB
M2 Ultra · 192 GBUD-IQ1_MRuns great129 GB28
M1 · 8 GBUD-IQ1_SToo big126 GB
M1 · 16 GBUD-IQ1_SToo big126 GB
M1 Pro · 16 GBUD-IQ1_SToo big126 GB
M1 Pro · 32 GBUD-IQ1_SToo big126 GB
M1 Max · 32 GBUD-IQ1_SToo big126 GB
M1 Max · 64 GBUD-IQ1_SToo big126 GB
M1 Ultra · 64 GBUD-IQ1_SToo big126 GB
M1 Ultra · 128 GBUD-IQ1_SToo big126 GB

Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.

Packaged by

2 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.

Information

Maker
reflection
Released
October 2026
Parameters
501B, 23B active
Longest chat
1M tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
6,944
Likes
18
Sizes
12, 103 to 1003 GB
Kind
Maker's release

Badge for the model card

Shows on Beam 1.0 501B A23B's Hugging Face card which Macs run it well, linked to this page. It updates every morning.

Runs on Mac badge

Files, downloads and likes read from Hugging Face on November 5, 2026 and refreshed every morning. Memory and speed are estimates until someone running Outmake measures this model on that Mac.

Your Computer

Every model is judged for this Mac. Both are under About This Mac, in the Apple menu.

Every Mac · Every graphics card

Civitai

Open in OutmakeHugging Face

New to Outmake? Download the free beta