unsloth
NVIDIA Nemotron 3.5 Bolt E4B
NVIDIA Nemotron 3.5 Bolt E4B is a 7.52B dense gemma4 model from unsloth. Configured context length is 131,072 tokens. License: other. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters7.5B
Context128K
Attentionhybrid
Licenseother
42 layers · 2 KV heads · head dim 256 · 35 sliding layers · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| BF16 | 14.0 GB | Hugging Face file bytes |
| UD-Q8_K_XL | 7.63 GB | Hugging Face file bytes |
| Q8_0 | 0.37 GB | Hugging Face file bytes |
| UD-Q6_K_XL | 6.76 GB | Hugging Face file bytes |
| UD-Q5_K_XL | 5.43 GB | Hugging Face file bytes |
| UD-Q4_K_XL | 4.71 GB | Hugging Face file bytes |
| UD-Q3_K_XL | 3.93 GB | Hugging Face file bytes |
| UD-IQ3_XXS | 3.45 GB | Hugging Face file bytes |
| UD-Q2_K_XL | 3.49 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Runs | UD-Q5_K_XL | 24–33 |
| GeForce RTX 3060 12GB | Runs | UD-Q8_K_XL | 22–30 |
| GeForce RTX 4060 Ti 16GB | Runs great | UD-Q8_K_XL | 18–24 |
| GeForce RTX 4090 | Runs | BF16 | 35–48 |
| GeForce RTX 5090 | Runs great | BF16 | 63–85 |
| Apple M4 Pro | Runs | BF16 | 9.5–13 |
| Apple M5 | Runs | UD-Q8_K_XL | 9.5–13 |
| CPU only · DDR5-5600 | Runs on CPU | BF16 | 3.1–4.3 |
Smallest devices that fit it fully
- GeForce RTX 3050 6GB — Runs, UD-Q3_K_XL, 19–26 tok/s
- GeForce RTX 2060 6GB — Runs, UD-Q3_K_XL, 38–51 tok/s
- GeForce GTX 1660 Super — Runs, UD-Q3_K_XL, 38–51 tok/s
- GeForce GTX 1660 Ti — Runs, UD-Q3_K_XL, 32–44 tok/s
- Intel Arc A380 — Runs, UD-Q3_K_XL, 21–28 tok/s
- GeForce RTX 5060 Ti 8GB — Runs, UD-Q5_K_XL, 38–51 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (UD-Q8_K_XL).
llama.cpp
llama-server -hf unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF:UD-Q8_K_XL -c 8192 -ngl 42
No matching name in the Ollama library snapshot.
LM Studio
lms get unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF # Then load quant UD-Q8_K_XL