NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF
NVIDIA-Nemotron-3.5-Bolt-E4B-4GB is a small language model (SLM) further post-trained from Gemma-4-E4B-it by NVIDIA. Nemotron-3.5-Bolt-E4B carries forward Gemma’s strong conversational capabilities and further improves multi-turn tool use, instruction following, and input grounding for fast local voice/device assistants, interactive personas, and embedded/edge interfaces. Designed for low-memory, low-TTFT operation,...
Params
4.0 B
Context
—
Downloads 30d
481 K
Likes
180
Download history
daily snapshots · 11 days481 K162 K
Oct 31Nov 3Nov 7Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| NVIDIA-Nemotron-3.5-Bolt-E4B-UD-IQ2_M.gguf | IQ2_M | 3.5 GB | 5.0 GB | ✅ Runs comfortably |
| NVIDIA-Nemotron-3.5-Bolt-E4B-UD-IQ3_XXS.gguf | IQ3_XXS | 3.7 GB | 5.2 GB | ✅ Runs comfortably |
| NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q2_K_XL.gguf | Q2_K_XL | 3.7 GB | 5.2 GB | ✅ Runs comfortably |
| NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q3_K_XL.gguf | Q3_K_XL | 4.2 GB | 5.7 GB | ✅ Runs comfortably |
| NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL.gguf | Q4_K_XL | 5.1 GB | 6.7 GB | ✅ Runs comfortably |
| NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q5_K_XL.gguf | Q5_K_XL | 5.8 GB | 7.5 GB | ✅ Runs comfortably |
| NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q6_K_XL.gguf | Q6_K_XL | 7.3 GB | 9.1 GB | ✅ Runs comfortably |
| NVIDIA-Nemotron-3.5-Bolt-E4B-BF16.gguf | GGUF | 15.1 GB | 17.7 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run nvidia-nemotron-3-5-bolt-e4b-gguf # pin the quantization explicitly $ ollama run nvidia-nemotron-3-5-bolt-e4b-gguf-q4_k_xl
$ huggingface-cli download unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF-GGUF \
NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL.gguf --local-dir .
$ llama-cli -m NVIDIA-Nemotron-3.5-Bolt-E4B-UD-Q4_K_XL.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/nvidia-nemotron-3-5-bolt-e4b-gguf
{
"hf_id": "unsloth/NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF",
"params_b": 4.00,
"context_length": null,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 481135,
"vram_estimates": [
{ "quant": "GGUF", "gb": 17.7 },
{ "quant": "IQ2_M", "gb": 5.0 }
],
"updated_at": "2026-10-31T01:00:17Z"
}
Specifications
- Parameters
- 4.0 B
- Licence
- other
- First seen on the Hub
- 2026-10-23
- Training datasets
- nvidia/nemotron-post-training-v3, nvidia/nemotron-pre-training-datasets
- Added to our catalog
- 2026-10-31
Compare with any text-generation model
Popular comparisons
Appears in