Can I run Meta Llama 3 70B Instruct locally?
Meta Llama 3 70B Instruct by meta-llama has 71B parameters. At 4-bit with an 8K context it needs about 43.3 GB of GPU memory. It fits on 25 of 65 GPUs and Macs we track. See all models that fit in 48 GB of VRAM.
GGUF Q8_0 file was 173% of the size expected from the parameter count, so this page uses size estimates instead of real file sizes.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx |
|---|---|---|---|
| 2-bit (Q2_K) | rough | 26.5 GB | 27.8 GB |
| 3-bit (Q3_K_M) | usable | 34.0 GB | 35.3 GB |
| 4-bit (Q4_K_M) | good, most popular | 42.1 GB | 43.3 GB |
| 5-bit (Q5_K_M) | very good | 48.7 GB | 50.0 GB |
| 6-bit (Q6_K) | near lossless | 55.8 GB | 57.0 GB |
| 8-bit (Q8_0) | effectively lossless | 71.7 GB | 73.0 GB |
| 16-bit (F16/BF16) | original weights | 133 GB | 135 GB |
Which GPUs and Macs run Meta Llama 3 70B Instruct?
Short answer with CPU offload and RAM needed: Can I run Llama 70B on my PC?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
Questions
How much VRAM does Meta Llama 3 70B Instruct need?
About 43.3 GB at 4-bit (Q4_K_M) with an 8K context: 40.2 GB of weights (estimated), 2.5 GB of KV cache and 0.6 GB of runtime overhead. At 8-bit it needs about 73.0 GB.
What is the smallest GPU that runs Meta Llama 3 70B Instruct?
No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the H100 PCIe (80 GB).
Can I run Meta Llama 3 70B Instruct on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M2 Max 96GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
Llama 3.3 70B Instruct
71B · 43.3 GB at 4-bitLlama 3.1 70B Instruct
71B · 42.7 GB at 4-bitLlama 3.1 70B
71B · 42.7 GB at 4-bitDeepSeek R1 Distill Llama 70B
71B · 43.3 GB at 4-bitApertus v1.5 70B
72B · 44.4 GB at 4-bitKimi Dev 72B
73B · 44.6 GB at 4-bitEmbed this
Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.
Copy a snippet
Markdown badge
[](https://runsonmy.com/model/meta-llama-3-70b-instruct/) Widget (script)
<div class="runsonmy-widget" data-model="meta-llama-3-70b-instruct"><a href="https://runsonmy.com/model/meta-llama-3-70b-instruct/">Will Meta Llama 3 70B Instruct run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script> Widget (iframe)
<iframe src="https://runsonmy.com/embed/m/meta-llama-3-70b-instruct/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Meta Llama 3 70B Instruct run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | meta-llama/Meta-Llama-3-70B-Instruct |
| Parameters | 70,553,706,496 (71B) |
| Layers / hidden size | 80 / 8192 |
| Attention | GQA; 64 heads, 8 KV heads, head dim 128 |
| KV cache per token (FP16) | 320.0 KiB |
| Max context | 8,192 tokens |
| License | llama3 (gated: accept terms on Hugging Face) |
| Released on HF | Apr 17, 2024 |
| Downloads (30d) / likes | 50,517 / 1,537 |
Sources: Hugging Face model API · config.json (FriendliAI/Meta-Llama-3-70B-Instruct-fp8) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.