Outmake Models
Models

MaziyarPanahi Topxtral 4x7B V0.1

RichardErkhov · June 2024

Get Hugging Face

A 19B, 13B active chat model from RichardErkhov.

Downloads
75K
Likes
1
Parameters
19B, 13B active
Context
32K

Runs well on M4 · 16 GB

The Q3_K_L size from RichardErkhov is the one to get: a 9.6 GB download that uses 10 GB of memory, and writes about 4.4 words a second.

MaziyarPanahi Topxtral 4x7B V0.1 runs well from a Mac with an M1 and 16 GB of memory. 56 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From RichardErkhov/MaziyarPanahi_-_Topxtral-4x7B-v0.1-gguf on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
Q2_K6.8 GB7.5 GBestimatedOpen
IQ3_XS7.6 GB8.3 GBestimatedOpen
Q3_K_S8.0 GB8.7 GBestimatedOpen
IQ3_S8.0 GB8.8 GBestimatedOpen
IQ3_M8.2 GB8.9 GBestimatedOpen
Q3_K8.9 GB9.6 GBestimatedOpen
Q3_K_M8.9 GB9.6 GBestimatedOpen
Q4_19.1 GB9.9 GBestimatedOpen
Q3_K_L9.6 GB10 GBestimatedOpen
IQ4_XS10 GB11 GBestimatedOpen
Q4_010 GB11 GBestimatedOpen
Q4_K_S11 GB11 GBestimatedOpen
IQ4_NL11 GB11 GBestimatedOpen
Q4_K11 GB12 GBestimatedOpen
Q4_K_M11 GB12 GBestimatedOpen

Run It Anywhere

MaziyarPanahi Topxtral 4x7B V0.1 is an open model, so any app that runs GGUF files can run it. These take the Q3_K_L size from RichardErkhov straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/RichardErkhov/MaziyarPanahi_-_Topxtral-4x7B-v0.1-gguf:Q3_K_L
  • llama.cppMac, Windows, Linuxllama-server -hf RichardErkhov/MaziyarPanahi_-_Topxtral-4x7B-v0.1-gguf:Q3_K_L
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/RichardErkhov/MaziyarPanahi_-_Topxtral-4x7B-v0.1-gguf:Q3_K_L
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 8.3 GB
8 GBNone worth runningneeds 8.3 GB
10 GBQ4_19.1 GB9.9 GB
11 GBIQ4_XS10 GB11 GB
12 GBIQ4_NL11 GB11 GB
16 GBQ4_K_M11 GB12 GB
20 GBQ4_K_M11 GB12 GB
24 GBQ4_K_M11 GB12 GB
32 GBQ4_K_M11 GB12 GB
48 GBQ4_K_M11 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 GBQ3_K_LRuns well10 GB6.1
M6 · 24 GBIQ4_NLRuns great11 GB5.8
M6 · 32 GBQ4_KRuns great14 GB5.6
M5 · 16 GBQ3_K_LRuns well10 GB5.6
M5 · 24 GBIQ4_NLRuns great11 GB5.3
M5 · 32 GBQ4_KRuns great14 GB5.1
M5 Pro · 24 GBIQ4_NLRuns great11 GB10
M5 Pro · 48 GBQ4_KRuns great14 GB10
M5 Pro · 64 GBQ4_KRuns great14 GB10
M5 Max · 36 GBQ4_KRuns great14 GB15
M5 Max · 48 GBQ4_KRuns great14 GB20
M5 Max · 64 GBQ4_KRuns great14 GB20
M5 Max · 128 GBQ4_KRuns great14 GB20
M5 Ultra · 96 GBQ4_KRuns great14 GB37
M5 Ultra · 256 GBQ4_KRuns great14 GB37
M5 Ultra · 512 GBQ4_KRuns great14 GB37
M4 · 16 GBQ3_K_LRuns well10 GB4.4
M4 · 24 GBIQ4_NLRuns great11 GB4.1
M4 · 32 GBQ4_KRuns great14 GB4
M4 Pro · 24 GBIQ4_NLRuns great11 GB8.9
M4 Pro · 48 GBQ4_KRuns great14 GB8.6
M4 Pro · 64 GBQ4_KRuns great14 GB8.6
M4 Max · 36 GBQ4_KRuns great14 GB12
M4 Max · 48 GBQ4_KRuns great14 GB16
M4 Max · 64 GBQ4_KRuns great14 GB16
M4 Max · 96 GBQ4_KRuns great14 GB12
M4 Max · 128 GBQ4_KRuns great14 GB16
M3 · 8 GBQ2_KToo big9.4 GB
M3 · 16 GBQ3_K_LRuns well10 GB3.7
M3 · 24 GBIQ4_NLRuns great11 GB3.5
M3 Pro · 18 GBQ4_KRuns well12 GB5
M3 Pro · 36 GBQ4_KRuns great14 GB5
M3 Max · 36 GBQ4_KRuns great14 GB9.5
M3 Max · 48 GBQ4_KRuns great14 GB12
M3 Max · 64 GBQ4_KRuns great14 GB12
M3 Max · 96 GBQ4_KRuns great14 GB9.5
M3 Max · 128 GBQ4_KRuns great14 GB12
M3 Ultra · 96 GBQ4_KRuns great14 GB22
M3 Ultra · 256 GBQ4_KRuns great14 GB22
M3 Ultra · 512 GBQ4_KRuns great14 GB22
M2 · 8 GBQ2_KToo big9.4 GB
M2 · 16 GBQ3_K_LRuns well10 GB3.7
M2 · 24 GBIQ4_NLRuns great11 GB3.5
M2 Pro · 16 GBQ3_K_LRuns well10 GB7.1
M2 Pro · 32 GBQ4_KRuns great14 GB6.5
M2 Max · 32 GBQ4_KRuns great14 GB12
M2 Max · 64 GBQ4_KRuns great14 GB12
M2 Max · 96 GBQ4_KRuns great14 GB12
M2 Ultra · 64 GBQ4_KRuns great14 GB22
M2 Ultra · 128 GBQ4_KRuns great14 GB22
M2 Ultra · 192 GBQ4_KRuns great14 GB22
M1 · 8 GBQ2_KToo big9.4 GB
M1 · 16 GBQ3_K_LRuns well10 GB2.5
M1 Pro · 16 GBQ3_K_LRuns well10 GB6.8
M1 Pro · 32 GBQ4_KRuns great14 GB6.3
M1 Max · 32 GBQ4_KRuns great14 GB11
M1 Max · 64 GBQ4_KRuns great14 GB11
M1 Ultra · 64 GBQ4_KRuns great14 GB19
M1 Ultra · 128 GBQ4_KRuns great14 GB19

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

Information

Maker
RichardErkhov
Released
June 2024
Parameters
19B, 13B active
Longest chat
32K tokens
Reads pictures
No
Licence
Not stated
Downloads this month
74,756
Likes
1
Sizes
15, 6.8 to 11 GB
Kind
Maker's release

Badge for the model card

Shows on MaziyarPanahi Topxtral 4x7B V0.1'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