Best Local LLMs for the NVIDIA A100 80GB

Written by Jakub Rusinowski · Last updated July 21, 2026

Best all-round pick: GPT-oss 120B

The NVIDIA A100 80GB has 80 GB of VRAM, of which about 80 GB is available to a model. The largest model it can hold is Devstral-2 123B (123B, 75.1 GB at Q4_K_M).

Best models overall on the NVIDIA A100 80GB

ModelScoreMemory at Q4_K_MContextLicence
GPT-oss 120B96.471.3 GB128KApache-2.0
Qwen 3.5 122B-A10B (MoE)94.474.5 GB125KApache 2.0
GLM-5.1 72B94.144.3 GB125KMIT
Qwen 3.5 72B93.744.3 GB125KApache 2.0
Llama 3.3 70B Instruct92.943.1 GB128KLlama Community
Qwen 3.5 122B-A10B92.874.5 GB128KApache-2.0

Best model by what you are doing

WorkloadRecommended on this GPU
CodingDevstral-2 123B (99.1)
Qwen3-Coder 80B-A3B (MoE) (98.6)
Qwen 3.5 122B-A10B (MoE) (96.8)
General assistantGPT-oss 120B (96.4)
Qwen 3.5 122B-A10B (MoE) (94.4)
GLM-5.1 72B (94.1)
ReasoningGLM-5.1 72B (100)
Qwen 3.5 122B-A10B (MoE) (97.1)
Gemma 4 27B ⭐ (96.8)
RAGLlama 4 Scout 17B (94.4)
Gemma 4 31B (94.1)
Llama 4.5 Scout (93.1)
AgentsDevstral-2 123B (95.3)
Ternary Bonsai 27B (90.1)
Nemotron-Cascade 2 30B-A3B (89.4)
VisionQwen 3.5 72B (99.2)
Llama 3.2 90B Vision Instruct (97.1)
Qwen 3.7 35B-A3B (94.5)

How these numbers are calculated

FAQ

What is the best LLM for the NVIDIA A100 80GB?

GPT-oss 120B is the strongest all-round pick that fits its 80 GB.

What is the largest model the NVIDIA A100 80GB can run?

Devstral-2 123B — 123B parameters, needing 75.1 GB at Q4_K_M.

How much of the NVIDIA A100 80GB's memory can a model actually use?

About 80 GB of its 80 GB, before the desktop and runtime overhead are accounted for.

Compatibility Checks for the NVIDIA A100 80GB

Similar GPUs

By Workload

More

← All GPUs | NVIDIA A100 80GB specs