Hugging FaceA 7.5B chat model from NVIDIA.
- Downloads
- 103K
- Likes
- 370
- Parameters
- 7.5B
- Context
- 64K
- Licence
- other
Runs great on M4 · 16 GB
The Q4_K_M size from nvidia is the one to get: a 6.2 GB download that uses 7.5 GB of memory, and writes about 9 words a second.
NVIDIA Nemotron 3.5 Bolt E4B 4GB 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 nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| Q4_K_M | 6.2 GB | 6.5 GBestimated | Open |
Run It Anywhere
NVIDIA Nemotron 3.5 Bolt E4B 4GB is an open model, so any app that runs GGUF files can run it. These take the Q4_K_M size from nvidia straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB:Q4_K_M - llama.cppMac, Windows, Linux
llama-server -hf nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB:Q4_K_M - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB:Q4_K_M
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 6.5 GB | |
| 8 GB | Q4_K_M | 6.2 GB | 6.5 GB |
| 10 GB | Q4_K_M | 6.2 GB | 6.5 GB |
| 11 GB | Q4_K_M | 6.2 GB | 6.5 GB |
| 12 GB | Q4_K_M | 6.2 GB | 6.5 GB |
| 16 GB | Q4_K_M | 6.2 GB | 6.5 GB |
| 20 GB | Q4_K_M | 6.2 GB | 6.5 GB |
| 24 GB | Q4_K_M | 6.2 GB | 6.5 GB |
| 32 GB | Q4_K_M | 6.2 GB | 6.5 GB |
| 48 GB | Q4_K_M | 6.2 GB | 6.5 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
| Mac | Size | Fit | Memory | Writes |
|---|---|---|---|---|
| M6 · 16 GB | Q4_K_M | Runs great | 7.5 GB | 13 |
| M6 · 24 GB | Q4_K_M | Runs great | 7.5 GB | 13 |
| M6 · 32 GB | Q4_K_M | Runs great | 7.5 GB | 13 |
| M5 · 16 GB | Q4_K_M | Runs great | 7.5 GB | 12 |
| M5 · 24 GB | Q4_K_M | Runs great | 7.5 GB | 12 |
| M5 · 32 GB | Q4_K_M | Runs great | 7.5 GB | 12 |
| M5 Pro · 24 GB | Q4_K_M | Runs great | 7.5 GB | 23 |
| M5 Pro · 48 GB | Q4_K_M | Runs great | 7.5 GB | 23 |
| M5 Pro · 64 GB | Q4_K_M | Runs great | 7.5 GB | 23 |
| M5 Max · 36 GB | Q4_K_M | Runs great | 7.5 GB | 33 |
| M5 Max · 48 GB | Q4_K_M | Runs great | 7.5 GB | 43 |
| M5 Max · 64 GB | Q4_K_M | Runs great | 7.5 GB | 43 |
| M5 Max · 128 GB | Q4_K_M | Runs great | 7.5 GB | 43 |
| M5 Ultra · 96 GB | Q4_K_M | Runs great | 7.5 GB | 78 |
| M5 Ultra · 256 GB | Q4_K_M | Runs great | 7.5 GB | 78 |
| M5 Ultra · 512 GB | Q4_K_M | Runs great | 7.5 GB | 78 |
| M4 · 16 GB | Q4_K_M | Runs great | 7.5 GB | 9 |
| M4 · 24 GB | Q4_K_M | Runs great | 7.5 GB | 9 |
| M4 · 32 GB | Q4_K_M | Runs great | 7.5 GB | 9 |
| M4 Pro · 24 GB | Q4_K_M | Runs great | 7.5 GB | 18 |
| M4 Pro · 48 GB | Q4_K_M | Runs great | 7.5 GB | 18 |
| M4 Pro · 64 GB | Q4_K_M | Runs great | 7.5 GB | 18 |
| M4 Max · 36 GB | Q4_K_M | Runs great | 7.5 GB | 25 |
| M4 Max · 48 GB | Q4_K_M | Runs great | 7.5 GB | 31 |
| M4 Max · 64 GB | Q4_K_M | Runs great | 7.5 GB | 31 |
| M4 Max · 96 GB | Q4_K_M | Runs great | 7.5 GB | 25 |
| M4 Max · 128 GB | Q4_K_M | Runs great | 7.5 GB | 31 |
| M3 · 8 GB | Q4_K_M | Too big | 7.5 GB | |
| M3 · 16 GB | Q4_K_M | Runs great | 7.5 GB | 7.7 |
| M3 · 24 GB | Q4_K_M | Runs great | 7.5 GB | 7.7 |
| M3 Pro · 18 GB | Q4_K_M | Runs great | 7.5 GB | 11 |
| M3 Pro · 36 GB | Q4_K_M | Runs great | 7.5 GB | 11 |
| M3 Max · 36 GB | Q4_K_M | Runs great | 7.5 GB | 20 |
| M3 Max · 48 GB | Q4_K_M | Runs great | 7.5 GB | 26 |
| M3 Max · 64 GB | Q4_K_M | Runs great | 7.5 GB | 26 |
| M3 Max · 96 GB | Q4_K_M | Runs great | 7.5 GB | 20 |
| M3 Max · 128 GB | Q4_K_M | Runs great | 7.5 GB | 26 |
| M3 Ultra · 96 GB | Q4_K_M | Runs great | 7.5 GB | 42 |
| M3 Ultra · 256 GB | Q4_K_M | Runs great | 7.5 GB | 42 |
| M3 Ultra · 512 GB | Q4_K_M | Runs great | 7.5 GB | 42 |
| M2 · 8 GB | Q4_K_M | Too big | 7.5 GB | |
| M2 · 16 GB | Q4_K_M | Runs great | 7.5 GB | 7.7 |
| M2 · 24 GB | Q4_K_M | Runs great | 7.5 GB | 7.7 |
| M2 Pro · 16 GB | Q4_K_M | Runs great | 7.5 GB | 14 |
| M2 Pro · 32 GB | Q4_K_M | Runs great | 7.5 GB | 14 |
| M2 Max · 32 GB | Q4_K_M | Runs great | 7.5 GB | 26 |
| M2 Max · 64 GB | Q4_K_M | Runs great | 7.5 GB | 26 |
| M2 Max · 96 GB | Q4_K_M | Runs great | 7.5 GB | 26 |
| M2 Ultra · 64 GB | Q4_K_M | Runs great | 7.5 GB | 42 |
| M2 Ultra · 128 GB | Q4_K_M | Runs great | 7.5 GB | 42 |
| M2 Ultra · 192 GB | Q4_K_M | Runs great | 7.5 GB | 42 |
| M1 · 8 GB | Q4_K_M | Too big | 7.5 GB | |
| M1 · 16 GB | Q4_K_M | Runs great | 7.5 GB | 5.2 |
| M1 Pro · 16 GB | Q4_K_M | Runs great | 7.5 GB | 13 |
| M1 Pro · 32 GB | Q4_K_M | Runs great | 7.5 GB | 13 |
| M1 Max · 32 GB | Q4_K_M | Runs great | 7.5 GB | 22 |
| M1 Max · 64 GB | Q4_K_M | Runs great | 7.5 GB | 22 |
| M1 Ultra · 64 GB | Q4_K_M | Runs great | 7.5 GB | 34 |
| M1 Ultra · 128 GB | Q4_K_M | Runs great | 7.5 GB | 34 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Information
- Maker
- NVIDIA
- Released
- October 2026
- Parameters
- 7.5B
- Longest chat
- 64K tokens
- Reads pictures
- No
- Licence
- other
- Downloads this month
- 103,117
- Likes
- 370
- Sizes
- 1, 6.2 to 6.2 GB
- Kind
- Maker's release
Badge for the model card
Shows on NVIDIA Nemotron 3.5 Bolt E4B 4GB's Hugging Face card which Macs run it well, linked to this page. It updates every morning.
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.