batiai/ nemotron3-super:iq4

51 Downloads Updated 2 months ago

ollama run batiai/nemotron3-super:iq4

curl http://localhost:11434/api/chat \
  -d '{
    "model": "batiai/nemotron3-super:iq4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='batiai/nemotron3-super:iq4',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'batiai/nemotron3-super:iq4',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 months ago

2 months ago

177b1785be5a · 66GB ·

model

archnemotron_h_moe

·

parameters121B

·

quantizationIQ4_XS

66GB

system

You are a helpful AI assistant.

31B

params

{ "num_ctx": 131072, "stop": [ "<extra_id_1>", "<|endoftext|>" ], "t

97B

Readme

Nemotron 3 Super 120B-A12B — Quantized by BatiAI

NVIDIA’s flagship NemotronH MoE (Mamba+Attention hybrid). 120B params, 12B active per token. For 96GB+ Macs. Quantized directly from official NVIDIA weights.

Models

Tag	Size	RAM target	Use Case
iq3	53GB	96GB Mac	Compact MoE
iq4	62GB	128GB Mac	Recommended

Quick Start

ollama run batiai/nemotron3-super:iq4

Why Nemotron 3 Super?

120B-A12B MoE — 12B active per token (vs 3B for Nano)
Hybrid Mamba + Attention — efficient long-context
Frontier reasoning + agentic — top-tier tool use
NVIDIA Open Model License — commercial-friendly

RAM Requirements

Your Mac RAM	iq3 (53GB)	iq4 (62GB)
64GB	⚠️ Heavy swap	❌
96GB	✅ Fast	⚠️ Tight
128GB	✅	✅ Recommended
192GB+	✅	✅ Headroom

Nemotron 3 Family

Model	Size	Active	Mac
`batiai/nemotron3-nano:iq4`	17GB	3B	32GB
`batiai/nemotron3-nano-omni-text:iq4`	17GB	3B (reasoning-tuned)	32GB
`batiai/nemotron3-super:iq4`	62GB	12B	128GB

Why BatiAI?

Quantized directly from official NVIDIA weights
imatrix calibrated (200 chunks wikitext-2)
Verified on real Mac hardware
BatiAI signed (general.author=BatiAI)

Built for BatiFlow

Free, on-device AI automation for Mac. 5MB app, 100% local, unlimited.

https://flow.bati.ai

# Nemotron 3 Super 120B-A12B — Quantized by BatiAI

NVIDIA's flagship NemotronH MoE (Mamba+Attention hybrid). 120B params, 12B active per token. For 96GB+ Macs.
Quantized directly from [official NVIDIA weights](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16).

## Models

| Tag | Size | RAM target | Use Case |
|-----|------|------------|----------|
| **iq3** | **53GB** | 96GB Mac | Compact MoE |
| **iq4** | **62GB** | 128GB Mac | **Recommended** |

## Quick Start

```
ollama run batiai/nemotron3-super:iq4
```

## Why Nemotron 3 Super?

- **120B-A12B MoE** — 12B active per token (vs 3B for Nano)
- **Hybrid Mamba + Attention** — efficient long-context
- **Frontier reasoning + agentic** — top-tier tool use
- NVIDIA Open Model License — commercial-friendly

## RAM Requirements

| Your Mac RAM | iq3 (53GB) | iq4 (62GB) |
|-------------|-----------|-----------|
| 64GB | ⚠️ Heavy swap | ❌ |
| **96GB** | **✅ Fast** | ⚠️ Tight |
| **128GB** | **✅** | **✅ Recommended** |
| 192GB+ | ✅ | ✅ Headroom |

## Nemotron 3 Family

| Model | Size | Active | Mac |
|-------|------|--------|-----|
| `batiai/nemotron3-nano:iq4` | 17GB | 3B | 32GB |
| `batiai/nemotron3-nano-omni-text:iq4` | 17GB | 3B (reasoning-tuned) | 32GB |
| **`batiai/nemotron3-super:iq4`** | **62GB** | **12B** | **128GB** |

## Why BatiAI?

- Quantized directly from official NVIDIA weights
- imatrix calibrated (200 chunks wikitext-2)
- Verified on real Mac hardware
- BatiAI signed (`general.author=BatiAI`)

## Built for BatiFlow

Free, on-device AI automation for Mac. 5MB app, 100% local, unlimited.

https://flow.bati.ai

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)