Llama-3.1-70B-Instruct
Meta Llama- Arena score
- 1261
- Among open models
- #100of 148
- Among all on Arena
- #295
- Votes
- 55,240
Measured on Llama 3.1 70B Instruct, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- English1294#98#27929.7K
- Legal & government1283#94#2693.2K
- Science1276#96#2799.4K
- Hard prompts, English1261#100#2919.1K
- French1261#76#242501
- Software & IT1260#101#29614.8K
- Coding1260#99#2949.4K
- Medicine & health1257#98#2762.8K
- Multi-turn1256#97#29110.4K
- Applied math1254#95#2846.5K
- Spanish1253#82#245606
- Math1252#92#2797.7K
- Hard prompts1241#101#29815K
- Long prompts1241#101#2987.6K
- Writing & literature1236#100#30015K
- Business & finance1235#99#2866.4K
- Russian1234#99#2967.3K
- Creative writing1232#96#2958.3K
- Instructions1231#101#29821.9K
- Media & sports1230#97#2888.7K
- German1222#80#2521.4K
- Non-English1219#100#30025.5K
- Chinese1215#100#3024.8K
- Expert1208#100#2892.9K
- Excluding ties1177#100#29334.8K
- Korean1141#78#250873
- Japanese1133#71#2451.4K
| Model | Params | Score |
|---|---|---|
| 8.0B | — | |
| 8.0B | 1187 | |
| 70.6B | 1261 | |
| 406B | 1284 |
About as strong, smaller
Compare
granite-4.2-3bIBM Granite12923.7B
gemma-3-4b-itGoogle12914.3B

gemma-3n-E4B-itGoogle13067.8B

Molmo2-8BAi212878.7B
Discussion
- Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPUxaskasdf · Feb 21, 2026395 points
- Comparativa LLM Local: Llama 3.1 vs Gemma 4 vs Qwen 3.8 ¿Cuál es el MEJOR?Ricardo Bertran · Sep 7, 2026205 likes
- Llama 3.1 8B ⚠️ ¿Sigue siendo VALIOSO o ya es OBSOLETO?Nichonauta · Sep 2, 202682 likes
- 🔥 Samsung научила память считать: Llama 3.1 ускорилась в 3 раза без новой GPU #ai #shortsAI Практика Pro · Aug 26, 202638 likes
- Build Your Own Local AI Chatbot on Mac | Open WebUI + Ollama + Llama 3.1ProgramGuru · Sep 17, 202622 likes
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM StudioMaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF37 builds
- MLX · Apple silicon: mlx-lm, LM Studiobaa-ai/Llama-3.1-70B-Instruct-SWAN-5bit-MLX1 build
- AWQ · vLLM, SGLangveeru2706/vritlellm-70b-gptq2 builds
- GPTQ · vLLM, SGLangRedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w4a162 builds
Most downloaded
- Meta-Llama-3.1-70B-Instruct-FP8RedHatAI · Quantization142.8K downloads
- Meta-Llama-3.1-70B-Instruct-GGUFMaziyarPanahi · Quantization38.4K downloads
- Meta-Llama-3.1-70B-Instruct-GGUFbartowski · Quantization36.8K downloads
- Llama-3.1-Nemotron-70B-Instruct-HFnvidia · Fine-tune13.7K downloads
- Meta-Llama-3.1-70B-Instructunsloth · Quantization4.3K downloads
BenchClub runs
Not runnable yet
Runs open once a Llama-3.1-70B-Instruct build is registered.
More from Meta Llama
See more
Llama-3.1-8B-Instruct4.2M8.0B

Llama-3.2-1B-Instruct1.3M1.2B

Llama-3.2-3B-Instruct831.4K3.2B

Llama-3.2-1B644.1K1.2B
Other 40–80B models
See more
Qwen3-Coder-NextQwen347.7K79.7B

Mixtral-8x7B-Instruct-v0.1Mistral AI325.3K46.7B

falcon-40bTII11.6K41.8B
Jamba-v0.1AI21 Labs4.5K51.6B