Outmake Models
Models

NVIDIA Nemotron 3.5 Bolt E4B

prithivMLmods · October 2026

Get Hugging Face

A 7.5B chat model from prithivMLmods that reads pictures as well as text.

Downloads
397K
Likes
176
Parameters
7.5B
Context
64K
Licence
other

Runs great on M4 · 16 GB

The UD-Q6_K_XL size from unsloth is the one to get: a 7.3 GB download that uses 7.7 GB of memory, and writes about 7.9 words a second.

NVIDIA Nemotron 3.5 Bolt E4B 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 bartowski/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ2_M3.1 GB3.4 GBestimatedOpen
Q2_K3.6 GB3.9 GBestimatedOpen
IQ3_XXS3.9 GB4.1 GBestimatedOpen
Q3_K_S3.9 GB4.2 GBestimatedOpen
IQ3_XS3.9 GB4.2 GBestimatedOpen
Q3_K_M4.1 GB4.3 GBestimatedOpen
Q3_K_L4.2 GB4.5 GBestimatedOpen
IQ3_M4.2 GB4.5 GBestimatedOpen
Q4_K_S4.9 GB5.2 GBestimatedOpen
IQ4_NL5.2 GB5.4 GBestimatedOpen
Q4_K_L5.3 GB5.6 GBestimatedOpen
Q4_15.5 GB5.7 GBestimatedOpen
Q6_K_S6.3 GB6.6 GBestimatedOpen
Q6_K_L6.6 GB6.9 GBestimatedOpen

Run It Anywhere

NVIDIA Nemotron 3.5 Bolt E4B is an open model, so any app that runs GGUF files can run it. These take the UD-Q6_K_XL size from unsloth straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:UD-Q6_K_XL
  • llama.cppMac, Windows, Linuxllama-server -hf unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:UD-Q6_K_XL
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:UD-Q6_K_XL
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBQ4_15.5 GB5.7 GB
8 GBQ6_K_L6.6 GB6.9 GB
10 GBQ6_K_L6.6 GB6.9 GB
11 GBQ6_K_L6.6 GB6.9 GB
12 GBQ6_K_L6.6 GB6.9 GB
16 GBQ6_K_L6.6 GB6.9 GB
20 GBQ6_K_L6.6 GB6.9 GB
24 GBQ6_K_L6.6 GB6.9 GB
32 GBQ6_K_L6.6 GB6.9 GB
48 GBQ6_K_L6.6 GB6.9 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-Q6_K_XLRuns great7.7 GB11
M6 · 24 GBQ8_0Runs great9.3 GB12
M6 · 32 GBQ8_0Runs great9.3 GB12
M5 · 16 GBUD-Q6_K_XLRuns great7.7 GB10
M5 · 24 GBQ8_0Runs great9.3 GB11
M5 · 32 GBQ8_0Runs great9.3 GB11
M5 Pro · 24 GBQ8_0Runs great9.3 GB22
M5 Pro · 48 GBQ8_0Runs great9.3 GB22
M5 Pro · 64 GBQ8_0Runs great9.3 GB22
M5 Max · 36 GBQ8_0Runs great9.3 GB32
M5 Max · 48 GBQ8_0Runs great9.3 GB42
M5 Max · 64 GBQ8_0Runs great9.3 GB42
M5 Max · 128 GBQ8_0Runs great9.3 GB42
M5 Ultra · 96 GBQ8_0Runs great9.3 GB77
M5 Ultra · 256 GBQ8_0Runs great9.3 GB77
M5 Ultra · 512 GBQ8_0Runs great9.3 GB77
M4 · 16 GBUD-Q6_K_XLRuns great7.7 GB7.9
M4 · 24 GBQ8_0Runs great9.3 GB8.3
M4 · 32 GBQ8_0Runs great9.3 GB8.3
M4 Pro · 24 GBQ8_0Runs great9.3 GB17
M4 Pro · 48 GBQ8_0Runs great9.3 GB17
M4 Pro · 64 GBQ8_0Runs great9.3 GB17
M4 Max · 36 GBQ8_0Runs great9.3 GB24
M4 Max · 48 GBQ8_0Runs great9.3 GB30
M4 Max · 64 GBQ8_0Runs great9.3 GB30
M4 Max · 96 GBQ8_0Runs great9.3 GB24
M4 Max · 128 GBQ8_0Runs great9.3 GB30
M3 · 8 GBQ4_K_SRuns well5.3 GB9.3
M3 · 16 GBUD-Q6_K_XLRuns great7.7 GB6.8
M3 · 24 GBQ8_0Runs great9.3 GB7.1
M3 Pro · 18 GBQ8_0Runs great8.4 GB10
M3 Pro · 36 GBQ8_0Runs great9.3 GB10
M3 Max · 36 GBQ8_0Runs great9.3 GB19
M3 Max · 48 GBQ8_0Runs great9.3 GB25
M3 Max · 64 GBQ8_0Runs great9.3 GB25
M3 Max · 96 GBQ8_0Runs great9.3 GB19
M3 Max · 128 GBQ8_0Runs great9.3 GB25
M3 Ultra · 96 GBQ8_0Runs great9.3 GB42
M3 Ultra · 256 GBQ8_0Runs great9.3 GB42
M3 Ultra · 512 GBQ8_0Runs great9.3 GB42
M2 · 8 GBQ4_K_SRuns well5.3 GB9.2
M2 · 16 GBUD-Q6_K_XLRuns great7.7 GB6.8
M2 · 24 GBQ8_0Runs great9.3 GB7.1
M2 Pro · 16 GBUD-Q6_K_XLRuns great7.7 GB13
M2 Pro · 32 GBQ8_0Runs great9.3 GB13
M2 Max · 32 GBQ8_0Runs great9.3 GB24
M2 Max · 64 GBQ8_0Runs great9.3 GB24
M2 Max · 96 GBQ8_0Runs great9.3 GB24
M2 Ultra · 64 GBQ8_0Runs great9.3 GB41
M2 Ultra · 128 GBQ8_0Runs great9.3 GB41
M2 Ultra · 192 GBQ8_0Runs great9.3 GB41
M1 · 8 GBQ4_K_SRuns well5.3 GB6.2
M1 · 16 GBUD-Q6_K_XLRuns great7.7 GB4.6
M1 Pro · 16 GBUD-Q6_K_XLRuns great7.7 GB12
M1 Pro · 32 GBQ8_0Runs great9.3 GB13
M1 Max · 32 GBQ8_0Runs great9.3 GB22
M1 Max · 64 GBQ8_0Runs great9.3 GB22
M1 Ultra · 64 GBQ8_0Runs great9.3 GB34
M1 Ultra · 128 GBQ8_0Runs great9.3 GB34

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

Packaged by

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

Information

Maker
prithivMLmods
Released
October 2026
Parameters
7.5B
Longest chat
64K tokens
Reads pictures
Yes
Licence
other
Downloads this month
396,830
Likes
176
Sizes
14, 3.1 to 6.6 GB
Kind
Maker's release

Badge for the model card

Shows on NVIDIA Nemotron 3.5 Bolt E4B'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