Best LLMs for 80 GB
Pick your memory. We rank every catalogued model that fits at its recommended quantization, by task, and show what the next tier up unlocks.
Written by Jakub Rusinowski · Last updated
Memory tier80 GBFor example A100 80GB (PCIe), H100 80GB (PCIe), H100 80GB (SXM)
Models that fit152entirely in memory
Best at 80 GB, by task
Score is the task-specific quality score on a 0–100 scale; speed is estimated for the A100 80GB (PCIe).
The strongest that fit
Top 15, by logic and coding
| Model | Memory · marker = 80 GB | VRAM | Speed on A100 80GB (PCIe) (est.) | Score |
|---|---|---|---|---|
| Qwen 2.5 72B Instruct Qwen 2.5 Family · Q4_K_M | 43.5 GB | ~25 tok/s | 98 | |
| Qwen 2.5 Coder 32B Qwen 2.5 Family · Q4_K_M | 19.3 GB | ~52 tok/s | 97 | |
| Llama 3.3 70B Instruct Llama 3.3 · Q2_K_XS (Tight) | 20.2 GB | ~50 tok/s | 97 | |
| Qwen 3 32B Qwen 3 · Q4_K_M | 19.8 GB | ~51 tok/s | 97 | |
| DeepSeek R1 Distill Qwen 32B DeepSeek R1 · Q4_K_M | 19.3 GB | ~52 tok/s | 96 | |
| Qwen 2.5 14B Instruct Qwen 2.5 Family · Q4_K_M | 8.5 GB | ~101 tok/s | 95 | |
| Nemotron 70B Instruct Nemotron 70B · Q4_K_M | 42.6 GB | ~26 tok/s | 94 | |
| Qwen 3 14B Qwen 3 · Q4_K_M | 8.9 GB | ~98 tok/s | 94 | |
| Qwen 3.5 122B-A10B Qwen 3.5 · Q4_K_M | 73.7 GB | ~118 tok/s | 93 | |
| Codestral 22B Codestral · Q4_K_M | 13.4 GB | ~71 tok/s | 93 | |
| Qwen 3.6 35B-A3B Qwen 3.6 · Q4_K_M | 21.1 GB | ~258 tok/s | 93 | |
| DeepSeek R1 Distill Qwen 14B DeepSeek R1 · Q4_K_M | 8.5 GB | ~102 tok/s | 92 | |
| Phi-4 (14B) Phi-4 Family · Q4_K_M | 8.5 GB | ~100 tok/s | 92 | |
| Gemma 4 31B Gemma 4 · Q4_K_M | 18.7 GB | ~52 tok/s | 92 | |
| Qwen 2.5 VL 72B Instruct Qwen 2.5 VL · Q4_K_M | 44.3 GB | ~25 tok/s | 92 |
FAQ
What LLMs run well with 80 GB VRAM?
Qwen 2.5 Family, Qwen 2.5 Family, Llama 3.3, Qwen 3, DeepSeek R1 all fit in 80 GB VRAM.
Which GPUs have 80 GB VRAM?
NVIDIA A100 80GB (PCIe), NVIDIA H100 80GB (PCIe), NVIDIA H100 80GB (SXM), NVIDIA RTX PRO 6000 Blackwell.
All tiers at a glance
| Memory | Models fit | Best overall | Largest that fits |
|---|---|---|---|
| 4 GB | 32 | Gemma 3 4B Instruct | Gemma 3 4B Instruct · 2.4 GB |
| 6 GB | 56 | Granite 3.0 8B Instruct | Qwen 2.5 VL 7B Instruct · 5 GB |
| 8 GB | 71 | Granite 3.0 8B Instruct | Falcon 3 10B Instruct · 6.2 GB |
| 10 GB | 83 | Qwen 2.5 14B Instruct | Qwen 3 14B · 8.9 GB |
| 12 GB | 85 | Qwen 2.5 14B Instruct | StarCoder 2 15B · 9.4 GB |
| 16 GB | 95 | Qwen 2.5 14B Instruct | Mistral Small 3 (24B) · 14.5 GB |
| 20 GB | 111 | Qwen 2.5 14B Instruct | Gemma 4 31B · 18.7 GB |
| 24 GB | 131 | Qwen 2.5 Coder 32B | Qwen 3.6 35B-A3B · 21.1 GB |
| 32 GB | 132 | Qwen 2.5 Coder 32B | Qwen 3.6 35B-A3B · 21.1 GB |
| 48 GB | 138 | Qwen 2.5 72B Instruct | Qwen 2.5 VL 72B Instruct · 44.3 GB |
| 64 GB | 143 | Qwen 2.5 72B Instruct | Qwen3-Coder-Next (80B-A3B MoE) · 48.3 GB |
| 80 GB | 152 | Qwen 2.5 72B Instruct | Qwen 3.5 122B-A10B · 73.7 GB |
Buy this hardware NVIDIA DGX Spark (128GB) — 128 GB VRAM · 150 W board powerDeploy in the cloud now NVIDIA A100 80GB on RunPod — from $1.39/hr · rate checked 2026-07
or compare on Vast.ai from $0.77/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Can-I-Run Pages Near 80 GB
- Nemotron 70B on NVIDIA A100 80GB (PCIe)
- Nemotron 70B on NVIDIA H100 80GB (PCIe)
- Command R Family on NVIDIA A100 80GB (PCIe)
- Command R Family on NVIDIA H100 80GB (PCIe)
- Qwen 2.5 Family on NVIDIA A100 80GB (PCIe)
- Qwen 2.5 Family on NVIDIA H100 80GB (PCIe)
- Llama 4 on NVIDIA A100 80GB (PCIe)
- Llama 4 on NVIDIA H100 80GB (PCIe)