All LLM Models
Browse 57 LLM models with VRAM requirements, quantization options, and hardware compatibility.
Understanding LLM VRAM Requirements
How much VRAM you need depends on the model size and quantization level. Quantization reduces the precision of model weights, trading small quality losses for significantly lower VRAM usage. For example, a 7B parameter model needs ~14 GB at FP16 but only ~4 GB at Q4_K_M quantization.
Model List
Nemotron Cascade 8B
NVIDIA · 8B · runs from 4 GB
31.7K
65Nemotron Cascade 8B is a 8B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 32,768 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron Labs Diffusion 14B
NVIDIA · 13.5B · runs from 6.5 GB
Nemotron Labs Diffusion 14B is a 13.5B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Llama 3 1 Nemotron Ultra 253B V1
NVIDIA · 253.4B · runs from 557.5 GB
Llama 3 1 Nemotron Ultra 253B V1 is a 253.4B-parameter open language model from NVIDIA in the Llama 3 family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
NVIDIA Nemotron 3 Super 120B A12B Base BF16
NVIDIA · 123.6B · runs from 53.0 GB
NVIDIA Nemotron 3 Super 120B A12B Base BF16 is a 123.6B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 1,048,576 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
OpenMath Nemotron 1.5B
NVIDIA · 1.5B · runs from 1.0 GB
OpenMath Nemotron 1.5B is a 1.5B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron Research Reasoning Qwen 1.5B
NVIDIA · 1.8B · runs from 1.1 GB
Nemotron Research Reasoning Qwen 1.5B is a 1.8B-parameter open language model from NVIDIA in the Qwen family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron Labs Audex 2B
NVIDIA · 2B · runs from 4.4 GB
Nemotron Labs Audex 2B is a 2B-parameter open language model from NVIDIA in the Nemotron family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron Terminal 8B
NVIDIA · 8.2B · runs from 4.1 GB
Nemotron Terminal 8B is a 8.2B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 40,960 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron Content Safety Reasoning 4B
NVIDIA · 4.3B · runs from 2.5 GB
Nemotron Content Safety Reasoning 4B is a 4.3B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Kimi K2.6 DFlash
NVIDIA · 3.5B · runs from 1.8 GB
Kimi K2.6 DFlash is a 3.5B-parameter open language model from NVIDIA in the Kimi K2 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron 3 Labs Ultra Math SFT
NVIDIA · 560.5B · runs from 238.8 GB
Nemotron 3 Labs Ultra Math SFT is a 560.5B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Llama 3.1 Nemotron Safety Guard 8B v3
NVIDIA · 8.0B · runs from 4.0 GB
Llama 3.1 Nemotron Safety Guard 8B v3 is a 8.0B-parameter open language model from NVIDIA in the Llama 3 family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Kimi K2.7 Code DFlash
NVIDIA · 3.5B · runs from 1.8 GB
Kimi K2.7 Code DFlash is a 3.5B-parameter open language model from NVIDIA in the Kimi K2 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron Terminal 32B
NVIDIA · 32.8B · runs from 14.6 GB
Nemotron Terminal 32B is a 32.8B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 40,960 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
NVIDIA Nemotron Labs 3 Puzzle 75B A9B BF16
NVIDIA · 75.4B · runs from 165.8 GB
NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16 is a deployment-optimized compression of NVIDIA's Nemotron-3-Super-120B-A12B, produced with Iterative Puzzle, a neural-architecture-search-based post-training compression framework, cutting the model from 120.7B total / 12.8B active parameters down to 75.3B total / roughly 9.3B active. It keeps the parent's hybrid architecture of interleaved Mamba, mixture-of-experts, and attention layers with multi-token prediction for faster generation, and the card reports about 2x higher server throughput on a single 8-GPU B200 node while only slightly trailing Nemotron-3-Super on reasoning, coding, agentic, and long-context benchmarks. It is a general-purpose reasoning and chat model intended for agents, chatbots, and RAG systems across seven languages, and needs a multi-GPU server to run. Context length defaults to 262,144 tokens in the published Hugging Face configuration, though the card states the architecture supports up to 1,048,576 tokens at higher memory cost. It is released under the OpenMDW License, version 1.1, a custom license for open model weights, and the card states it was published on July 6, 2026.
OpenReasoning Nemotron 32B
NVIDIA · 32.8B · runs from 14.8 GB
OpenReasoning Nemotron 32B is a 32.8B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron H 8B Reasoning 128K
NVIDIA · 8.1B · runs from 17.8 GB
Nemotron H 8B Reasoning 128K is a 8.1B-parameter open language model from NVIDIA in the Nemotron family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Llama 3 1 Nemotron 51B Instruct
NVIDIA · 51B · runs from 112.2 GB
Llama 3 1 Nemotron 51B Instruct is a 51B-parameter open language model from NVIDIA in the Llama 3 family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Kimi K2.6 Eagle3
NVIDIA · 1.8B · runs from 1.1 GB
Kimi K2.6 Eagle3 is a 1.8B-parameter open language model from NVIDIA in the Kimi K2 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron H 47B Reasoning 128K
NVIDIA · 46.8B · runs from 102.9 GB
Nemotron H 47B Reasoning 128K is a 46.8B-parameter open language model from NVIDIA in the Nemotron family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron Terminal 14B
NVIDIA · 14.8B · runs from 6.9 GB
Nemotron Terminal 14B is a 14.8B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 40,960 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3 Nemotron 235B A22B GenRM 2603
NVIDIA · 235.1B · runs from 100.4 GB
Qwen3 Nemotron 235B A22B GenRM 2603 is a 235.1B-parameter open language model from NVIDIA in the Qwen 3 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
NVIDIA Nemotron 3 Ultra 550B A55B GenRM
NVIDIA · 560.5B · runs from 262.1 GB
NVIDIA Nemotron 3 Ultra 550B A55B GenRM is a 560.5B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Nemotron Flash 3B
NVIDIA · 2.7B · runs from 6.0 GB
Nemotron Flash 3B is a 2.7B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 29,000 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
OpenCodeReasoning Nemotron 1.1 32B
NVIDIA · 32.8B · runs from 14.8 GB
OpenCodeReasoning Nemotron 1.1 32B is a 32.8B-parameter open language model from NVIDIA in the Nemotron family. It supports a context window of up to 65,536 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Riva Translate 4B Instruct
NVIDIA · 4.2B · runs from 2.3 GB
Riva Translate 4B Instruct is a 4.2B-parameter open language model from NVIDIA. It supports a context window of up to 8,192 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Llama 3.3 Nemotron 70B Reward
NVIDIA · 70.6B · runs from 31.0 GB
Llama 3.3 Nemotron 70B Reward is a 70.6B-parameter open language model from NVIDIA in the Llama 3 family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.