Outmake Models
Models

SOLAR 10.7B V1.0

Upstage · December 2023

Get Hugging Face

A 11B chat model from Upstage.

Rating
2.0
Downloads
3.2K
Likes
84
Parameters
11B
Context
4K
Licence
cc-by-nc-4.0

Runs great on M4 · 16 GB

The Q4_K_M size from TheBloke is the one to get: a 6.5 GB download that uses 7.0 GB of memory, and writes about 5.3 words a second.

Ratings

2.0 out of 5, across people's blind votes on its answers.

Text
1152

LM Arena ratings of October 28, 2026 (CC BY 4.0): people vote between two answers without knowing which model wrote which. The bar ends at 1488, the best any open model has. The Arena tests the full model; a small size on a Mac answers a little worse.

SOLAR 10.7B V1.0 runs well from a Mac with an M1 and 8 GB of memory. 59 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From TheBloke/SOLAR-10.7B-Instruct-v1.0-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
Q2_K4.5 GB5.6 GBestimatedOpen
Q3_K_S4.7 GB5.7 GBestimatedOpen
Q3_K_M5.2 GB6.2 GBestimatedOpen
Q3_K_L5.7 GB6.7 GBestimatedOpen
Q4_06.1 GB7.1 GBestimatedOpen
Q4_K_S6.1 GB7.1 GBestimatedOpen
Q4_K_M6.5 GB7.5 GBestimatedOpen
Q5_07.4 GB8.4 GBestimatedOpen
Q5_K_S7.4 GB8.4 GBestimatedOpen
Q5_K_M7.6 GB8.6 GBestimatedOpen
Q6_K8.8 GB9.8 GBestimatedOpen
Q8_011 GB12 GBestimatedOpen

Run It Anywhere

SOLAR 10.7B V1.0 is an open model, so any app that runs GGUF files can run it. These take the Q4_K_M size from TheBloke straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/TheBloke/SOLAR-10.7B-Instruct-v1.0-GGUF:Q4_K_M
  • llama.cppMac, Windows, Linuxllama-server -hf TheBloke/SOLAR-10.7B-Instruct-v1.0-GGUF:Q4_K_M
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/TheBloke/SOLAR-10.7B-Instruct-v1.0-GGUF:Q4_K_M
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBQ3_K_S4.7 GB5.7 GB
8 GBQ4_K_M6.5 GB7.5 GB
10 GBQ6_K8.8 GB9.8 GB
11 GBQ6_K8.8 GB9.8 GB
12 GBQ6_K8.8 GB9.8 GB
16 GBQ8_011 GB12 GB
20 GBQ8_011 GB12 GB
24 GBQ8_011 GB12 GB
32 GBQ8_011 GB12 GB
48 GBQ8_011 GB12 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 GBQ4_K_MRuns great7.0 GB7.5
M6 · 24 GBQ6_KRuns great9.4 GB6.6
M6 · 32 GBQ8_0Runs great12 GB6.4
M5 · 16 GBQ4_K_MRuns great7.0 GB6.8
M5 · 24 GBQ6_KRuns great9.4 GB6
M5 · 32 GBQ8_0Runs great12 GB5.8
M5 Pro · 24 GBQ6_KRuns great9.4 GB12
M5 Pro · 48 GBQ8_0Runs great12 GB11
M5 Pro · 64 GBQ8_0Runs great12 GB11
M5 Max · 36 GBQ8_0Runs great12 GB17
M5 Max · 48 GBQ8_0Runs great12 GB22
M5 Max · 64 GBQ8_0Runs great12 GB22
M5 Max · 128 GBQ8_0Runs great12 GB22
M5 Ultra · 96 GBQ8_0Runs great12 GB42
M5 Ultra · 256 GBQ8_0Runs great12 GB42
M5 Ultra · 512 GBQ8_0Runs great12 GB42
M4 · 16 GBQ4_K_MRuns great7.0 GB5.3
M4 · 24 GBQ6_KRuns great9.4 GB4.5
M4 · 32 GBQ8_0Runs great12 GB4.4
M4 Pro · 24 GBQ6_KRuns great9.4 GB9.6
M4 Pro · 48 GBQ8_0Runs great12 GB9.4
M4 Pro · 64 GBQ8_0Runs great12 GB9.4
M4 Max · 36 GBQ8_0Runs great12 GB14
M4 Max · 48 GBQ8_0Runs great12 GB17
M4 Max · 64 GBQ8_0Runs great12 GB17
M4 Max · 96 GBQ8_0Runs great12 GB14
M4 Max · 128 GBQ8_0Runs great12 GB17
M3 · 8 GBQ3_K_SRuns well5.2 GB5.1
M3 · 16 GBQ4_K_MRuns great7.0 GB4.5
M3 · 24 GBQ6_KRuns great9.4 GB3.8
M3 Pro · 18 GBQ5_K_MRuns great8.2 GB6
M3 Pro · 36 GBQ8_0Runs great12 GB5.5
M3 Max · 36 GBQ8_0Runs great12 GB10
M3 Max · 48 GBQ8_0Runs great12 GB14
M3 Max · 64 GBQ8_0Runs great12 GB14
M3 Max · 96 GBQ8_0Runs great12 GB10
M3 Max · 128 GBQ8_0Runs great12 GB14
M3 Ultra · 96 GBQ8_0Runs great12 GB24
M3 Ultra · 256 GBQ8_0Runs great12 GB24
M3 Ultra · 512 GBQ8_0Runs great12 GB24
M2 · 8 GBQ3_K_SRuns well5.2 GB5.1
M2 · 16 GBQ4_K_MRuns great7.0 GB4.5
M2 · 24 GBQ6_KRuns great9.4 GB3.8
M2 Pro · 16 GBQ4_K_MRuns great7.0 GB8.5
M2 Pro · 32 GBQ8_0Runs great12 GB7.2
M2 Max · 32 GBQ8_0Runs great12 GB14
M2 Max · 64 GBQ8_0Runs great12 GB14
M2 Max · 96 GBQ8_0Runs great12 GB14
M2 Ultra · 64 GBQ8_0Runs great12 GB24
M2 Ultra · 128 GBQ8_0Runs great12 GB24
M2 Ultra · 192 GBQ8_0Runs great12 GB24
M1 · 8 GBQ3_K_SRuns well5.2 GB3.5
M1 · 16 GBQ4_K_MRuns great7.0 GB3
M1 Pro · 16 GBQ4_K_MRuns great7.0 GB8.1
M1 Pro · 32 GBQ8_0Runs great12 GB6.9
M1 Max · 32 GBQ8_0Runs great12 GB13
M1 Max · 64 GBQ8_0Runs great12 GB13
M1 Ultra · 64 GBQ8_0Runs great12 GB21
M1 Ultra · 128 GBQ8_0Runs great12 GB21

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

Information

Maker
Upstage
Released
December 2023
Parameters
11B
Longest chat
4K tokens
Reads pictures
No
Licence
cc-by-nc-4.0
Downloads this month
3,160
Likes
84
Sizes
12, 4.5 to 11 GB
Kind
Maker's release

Badge for the model card

Shows on SOLAR 10.7B V1.0'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