Rent a GPU

Can the NVIDIA RTX 4070 Super run Llama 3.2 1B?

RTX 4070 Super × Llama 3.2 1B8K context
YesRuns fully on the GPU
Memory at FP163.3 GB of 12 GB
Weights 2.5 GBKV cache 0.3 GBRuntime 0.6 GB
QuantFP16Full quality
Speed~122tokens per second
Max context128Kthe model's full window
  1. FP16
  2. Q8_0
  3. Q6_K
  4. Q5_K_M
  5. Q4_K_M
  6. Q3_K_M
  7. Q2_K

Yes. The NVIDIA RTX 4070 Super can run Llama 3.2 1B fully in VRAM at FP16 (full quality), using about 3.3 GB of the 12 GB available, at roughly 122 tokens/second.

Try other context lengths

Run it with Ollama

With Ollama installed, one command downloads and starts Llama 3.2 1B:

ollama run llama3.2:1b

Ollama's default download is Q4_K_M (about 1.6 GB here). You have room for FP16, which is full quality: pick that GGUF in LM Studio or from Hugging Face.

New to this? Step-by-step setup for the RTX 4070 Super

Run it in the cloud

No NVIDIA RTX 4070 Super? Run Llama 3.2 1B in the cloud.

Rent a cloud GPU by the hour. No upfront cost, stop any time.

Rent a GPU on RunPodRent a GPU on Vast.ai

Memory needed by quantization

At 8,192 tokens of context. The black line marks the 12 GB the NVIDIA RTX 4070 Super can use.

QuantQualityMemoryFits?Speed
FP16Full quality3.3 GBFits~122 tok/s
Q8_0Near-lossless2.2 GBFits~230 tok/s
Q6_KExcellent1.9 GBFits~297 tok/s
Q5_K_MVery good1.8 GBFits~343 tok/s
Q4_K_MGood, most popular1.6 GBFits~402 tok/s
Q3_K_MNoticeably degraded1.5 GBFits~499 tok/s
Q2_KHeavily degraded1.3 GBFits~650 tok/s

Measured speed from real RTX 4070 Super owners

Tokens per second that people measured on their own NVIDIA RTX 4070 Super, next to our estimate.

No one has measured Llama 3.2 1B on the NVIDIA RTX 4070 Super yet. The speeds above are estimates. Run the benchmark and yours becomes the first real number on this page.

Have an RTX 4070 Super? Add your real speed

One command times Llama 3.2 1B in your own Ollama, shows you exactly what it would send, and asks before sending anything. No sign-up, no personal data.

macOS and Linux

curl -fsSL https://gpufit.dev/bench.sh | sh -s -- llama3.2:1b

Windows (PowerShell)

$env:GPUFIT_MODEL="llama3.2:1b"; irm https://gpufit.dev/bench.ps1 | iex

How the benchmark works

GPUs that run Llama 3.2 1B comfortably

Models that run well on the NVIDIA RTX 4070 Super

Frequently asked questions

Can NVIDIA RTX 4070 Super run Llama 3.2 1B?

Yes. The NVIDIA RTX 4070 Super can run Llama 3.2 1B fully in VRAM at FP16 (full quality), using about 3.3 GB of the 12 GB available, at roughly 122 tokens/second.

How much VRAM does Llama 3.2 1B need?

About 1.6 GB at Q4_K_M with 8,192 tokens of context, and about 3.3 GB at full FP16 precision.

How fast is Llama 3.2 1B on the NVIDIA RTX 4070 Super?

Roughly 122 tokens per second at FP16, estimated from the NVIDIA RTX 4070 Super's 504 GB/s memory bandwidth.