Llama 3.1 Nemotron Nano VL 8B V1 — Hardware Requirements & GPU Compatibility
VisionNVIDIA has released Llama 3.1 Nemotron Nano VL 8B, an 8-billion-parameter vision-language model focused on document intelligence. This system pairs a C-RADIOv2-H vision encoder with the Llama-3.1-8B-Instruct language model. Key use cases include image summarization, text-image analysis, optical character recognition, interactive question answering, and text chain-of-thought reasoning. The model supports single-image inference in English only; according to the card, a 4-bit AWQ build can run on Jetson Orin devices or laptops. At this size, it fits onto a single consumer GPU once quantization is applied. The specifications call for an input plus output budget of 16K tokens. Use follows the NVIDIA Open Model License, with the Llama 3.1 Community Model License also in effect; additionally, the card requires a "Built with Llama" notice. It was published in June 2025. NVIDIA's documentation points to Nemotron Nano v2 12B VL as the newer alternative.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 8K)Best on 24 GB (Q4_K_M · ~114 tok/s · 32K)Macs from 16 GB (Q4_K_M · ~24 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Llama 3.1 Nemotron Nano VL 8B V1
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/forkjoin-ai/llama-3.1-nemotron-nano-vl-8b-v1-gguf:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 15.6 GB free · 16K context
Download: nvidia_Llama-3.1-Nemotron-Nano-8B-v1-Q4_K_M.gguf4.92 GBforkjoin-ai
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 5070 Ti (16 GB) (7 GB headroom) · Q4_K_M
- Generation speed
- ~101 tok/s
- generation speed
- Cost per 1M output tokens
- $0.45
- per 1M output tokens
How Much VRAM Does Llama 3.1 Nemotron Nano VL 8B V1 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.1 GB | 9.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~161 tok/s | |
| 4.7 GB | 10.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~140 tok/s | |
| 5.8 GB | 11.4 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~114 tok/s | |
| 6.8 GB | 12.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~96 tok/s | |
| 7.9 GB | 13.6 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~83 tok/s | |
| 9.6 GB | 15.2 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~68 tok/s | |
| 19.2 GB | 24.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 16K context · ~34 tok/s |
Selected Q4_K_M
4-bit medium quantization8.4GBat 16K context
- Weights
- 5.1 GB
- KV cache
- 3.0 GB
- Overhead
- 0.3 GB
Which Hardware Can Run Llama 3.1 Nemotron Nano VL 8B V1?
Q4_K_M · 5.8 GBLlama 3.1 Nemotron Nano VL 8B V1 (Q4_K_M) requires 5.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. 107 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 172 devices with unified memory can run Llama 3.1 Nemotron Nano VL 8B V1, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), NVIDIA Jetson Orin Nano 8GB (Super).
12 GB
12 GB tier →fits · 3.6 GB free · up to 32K ctx
16 GPUs · 1 device family
RTX 3080 Ti~103Simulate output on RTX 3080 TiRTX 3080 12GB~103Simulate output on RTX 3080 12GBRTX 5070~76Simulate output on RTX 5070iPhone~9Simulate output on Apple iPhone 17 Pro20 GB
fits · 11.6 GB free · up to 32K ctx
1 GPU
RX 7900 XT~83Simulate output on RX 7900 XT32–40 GB
fits · 23.6 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~202Simulate output on RTX 5090M5 Max*36 GB~56Simulate output on Mac Studio M5 Max (36 GB)M632 GB~21Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~34Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~23Simulate output on NVIDIA Jetson AGX Orin 32GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Llama 3.1 Nemotron Nano VL 8B V1
Llama 3 family · 65 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Granite Switch 4.1 8BIBM | — | 8.4 GB | ~111 | same size |
| ALoDLM 8BAmazon | — | 7.6 GB | ~119 | same size |
| Llm Jp 4.1 8B Thinkingllm-jp | — | 7.6 GB | ~115 | same size |
| Apertus V1.5 8Bswiss-ai | — | 8.5 GB | ~111 | same size |
| Ornith 1.0 9BDeep Reinforce | — | 6.5 GB | ~106 | same size |
| LFM2.5 8B A1BLiquid AI | — | 5.6 GB | ~335 | same size |
Specifications
- Publisher
- NVIDIA
- Family
- Llama 3
- Parameters
- 8.7B
- Architecture
- Llama_Nemotron_Nano_VL
- Release Date
- 2025-06-03
- License
- Other
Frequently Asked Questions
How much VRAM does Llama 3.1 Nemotron Nano VL 8B V1 need?
Llama 3.1 Nemotron Nano VL 8B V1 requires 5.8 GB of VRAM at Q4_K_M, or 19.2 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 8.7B × 4.8 bits ÷ 8 = 5.2 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
What's the best quantization for Llama 3.1 Nemotron Nano VL 8B V1?
For Llama 3.1 Nemotron Nano VL 8B V1, Q4_K_M (5.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (6.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 4.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Llama 3.1 Nemotron Nano VL 8B V1 on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 145 other Macs can run Llama 3.1 Nemotron Nano VL 8B V1. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Llama 3.1 Nemotron Nano VL 8B V1 locally?
Yes — Llama 3.1 Nemotron Nano VL 8B V1 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Llama 3.1 Nemotron Nano VL 8B V1?
At Q4_K_M, Llama 3.1 Nemotron Nano VL 8B V1 can reach ~833 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~114 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 5.76 × 0.65 = ~903 tok/s
Estimated speed at Q4_K_M (5.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Llama 3.1 Nemotron Nano VL 8B V1?
At Q4_K_M, the download is about 5.23 GB. The full-precision BF16 version is 17.44 GB. The smallest option (Q2_K) is 3.71 GB.
Which GPUs can run Llama 3.1 Nemotron Nano VL 8B V1?
107 consumer GPUs can run Llama 3.1 Nemotron Nano VL 8B V1 at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6700M, AMD Radeon RX 6750 XT, AMD Radeon RX 5600 XT. 51 GPUs have plenty of headroom for comfortable inference.
Which devices can run Llama 3.1 Nemotron Nano VL 8B V1?
172 devices with unified memory can run Llama 3.1 Nemotron Nano VL 8B V1 at Q4_K_M (5.8 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.