Llama 3.1 70B
A 71 billion-parameterHow many numbers the model learned during training — the usual rough measure of its size. dense model from Meta. 8B, 70B and 405B models with 128K context.
- Size
- 70.6Bdense
- Memory to run
- ~42 GB estimatesmallest, 8K ctx
- Context
- 128Ktokens
- License
- RestrictedLlama 3.1 Community License
- Updated
- 18 Sept 2026
Where it runs
Best-fitting version on each reference system, at an 8K contextHow much text the model can consider at once, counted in tokens — roughly ¾ of a word each..
Runs well 7
- A100 80GB server~30 tok/s estimate
- Dual RTX 3090~13 tok/s estimate
- GB10 mini workstation~4 tok/s estimate
- MacBook Pro M3 Max 64 GB~6 tok/s estimate
- MacBook Pro M4 Max 128 GB~8 tok/s estimate
- Mac Studio M2 Ultra 192 GB~12 tok/s estimate
- Ryzen AI Max+ 395 mini PC~4 tok/s estimate
Slowly (CPU or offload) 4
- CPU-only Ryzen 9 7950X~1 tok/s estimate
- RTX 4090 workstation~2 tok/s estimate
- RTX 5090 workstation~4 tok/s estimate
- RX 7900 XTX desktop~2 tok/s estimate
Measured throughput
Versions & downloads
Each version is a separate set of weights. Expand one for its downloads: quantizationStoring each of the model’s numbers with fewer bits, so the file is smaller and needs less memory. trades a little quality for a much smaller file, and the memory column adds the working memoryExtra space the model needs while it answers. It grows with the length of the conversation, on top of the file itself. a conversation needs on top.
Variant Llama 3.1 70B InstructRestricted
- Good for
- Publisher
- Meta
- License
- Llama 3.1 Community License · commercial use restricted
- Released
- 23 Jul 2024
- huggingface
- meta-llama/Llama-3.1-70B-Instruct
Contributions are not open yet, so there is nothing here from members.
| Quantization | Format | Bits | Download | Memory @ 8K | Publisher |
|---|---|---|---|---|---|
| Download BF16native | safetensors | 16 | 131 GiB | Metameta-llama/Llama-3.1-70B-Instruct | |
| Download Q4_K_Mk quant | gguf | 4.89 | 40.2 GiB | LM Studio Communitylmstudio-community/Llama-3.1-70B-Instruct-GGUF | |
| Download MLX 4-bitmlx | mlx | 4.5 | 37.0 GiB | MLX Communitymlx-community/Llama-3.1-70B-Instruct-4bit |
Other sizes in Llama 3.1: Llama 3.1 8B
Benchmarks
Each benchmarkA fixed set of questions every model is given, so their scores can be compared on the same task. score is labelled with who produced it. Developer-reported scores use each lab’s own prompts and settings; a benchmark that runs every model itself uses one setup for all. Bars are relative to the best open result.
Community
Benchmark runs and reviews from people running it on their own hardware.
Benchmark runs
Reviews
Details & sources
Architecture
- Parameters
- 70.55B
- Active / token
- All (dense)
- Architecture
- Dense
- Layers
- 80
- Attention heads
- 64
- KV heads
- 8
- Head dim
- 128
- KV cache @ 8K (fp16)
- 2.50 GiB
- Max context
- 131,072 tokens
Lineage
How this model’s versions relate to each other and to other models.
Sources
- Hugging Face Hub (live source, 1 record, 18 Sept 2026)
- Mutinai illustrative fixtures (illustrative fixture, 1 record, 13 Sept 2026)
External identifiers
- huggingface meta-llama/Llama-3.1-70B-Instruct
Field history
- license = "llama3.1" — Hugging Face Hub (current)
Timeline
- Hermes 3 fine-tunes of Llama 3.1 released
- Meta releases Llama 3.1 (8B, 70B, 405B)