A100 80GB for local LLMs — what fits in 80 GB & the real cost

Rent a A100 80GB from $1.39/hr ($0 markup, as of 2026-07-02). 365 of the 421 models in our catalog fit its 80 GB — plus the honest own-vs-rent-vs-API math, electricity and amortization included.

Three honest ways to run AI on a A100 80GB

• Own it: buy the card and pay electricity + amortization — local is real money, not "$0".
• Rent it: from $1.39/GPU-hr on your own vendor account (as of 2026-07-02, $0 markup — we never resell compute).
• Skip it: run a comparable open model through your own API key, paying per million tokens (prices as of 2026-06-29).

Rent a A100 80GB — real vendor rates, $0 markup

• RunPod: $1.39/GPU-hr — vendor's own price as of 2026-07-02; you pay them directly.
• Crusoe: $2.00/GPU-hr — vendor's own price as of 2026-07-02; you pay them directly.

What fits in 80 GB

• 365 of the 421 models in the Spanvero catalog fit on one A100 80GB at a sensible quant (context capped at 16k for the estimate). Most capable first:
• gpt-oss-120b (OpenAI, 117B) — ~80 GB at Q4_K_M; own-key API alternative ≈ $0.09/1M tokens.
• GLM 4.5 Air (zai-org, 110.5B) — ~76 GB at Q4_K_M; own-key API alternative ≈ $0.49/1M tokens.
• Llama 4 Scout (17B-16E) (Meta, 109B) — ~77 GB at Q4_K_M; own-key API alternative ≈ $0.20/1M tokens (last-known).
• sarvam 105b (sarvamai, 106B) — ~80 GB at Q4_K_M; own-key API alternative ≈ $0.95/1M tokens (size estimate).
• Command R+ (08-2024) (Cohere, 104B) — ~75 GB at Q4_K_M; own-key API alternative ≈ $0.93/1M tokens (size estimate).
• LLaDA2.1 flash (inclusionAI, 102.9B) — ~71 GB at Q4_K_M; own-key API alternative ≈ $0.92/1M tokens (size estimate).
• Qwen3 Next 80B A3B Instruct (Qwen, 81.3B) — ~56 GB at Q4_K_M; own-key API alternative ≈ $0.60/1M tokens.
• Qwen3 Coder Next (Qwen, 79.7B) — ~55 GB at Q4_K_M; own-key API alternative ≈ $0.46/1M tokens.
• Qwen2.5 72B Instruct (Alibaba, 72B) — ~54 GB at Q4_K_M; own-key API alternative ≈ $0.68/1M tokens (size estimate).
• Meta Llama 3.1 70B Instruct quantized.w4a16 (RedHatAI, 70.6B) — ~54 GB at Q4_K_M; own-key API alternative ≈ $0.66/1M tokens (size estimate).
• DeepSeek R1 Distill Llama 70B (deepseek-ai, 70.6B) — ~54 GB at Q4_K_M; own-key API alternative ≈ $0.80/1M tokens.
• Hermes 3 Llama 3.1 70B (NousResearch, 70.6B) — ~54 GB at Q4_K_M; own-key API alternative ≈ $0.70/1M tokens.
• Llama 3.1 70B Instruct (Meta, 70B) — ~53 GB at Q4_K_M; own-key API alternative ≈ $0.40/1M tokens.
• Llama 3.3 70B Instruct (Meta, 70B) — ~53 GB at Q4_K_M; own-key API alternative ≈ $0.21/1M tokens.
• StableBeluga2 (petals-team, 69B) — ~48 GB at Q4_K_M; own-key API alternative ≈ $0.65/1M tokens (size estimate).

• gpt-oss-120b — full cost breakdown
• GLM 4.5 Air — full cost breakdown
• Llama 4 Scout (17B-16E) — full cost breakdown
• sarvam 105b — full cost breakdown
• Command R+ (08-2024) — full cost breakdown
• LLaDA2.1 flash — full cost breakdown
• Qwen3 Next 80B A3B Instruct — full cost breakdown
• Qwen3 Coder Next — full cost breakdown
• Qwen2.5 72B Instruct — full cost breakdown
• Meta Llama 3.1 70B Instruct quantized.w4a16 — full cost breakdown
• DeepSeek R1 Distill Llama 70B — full cost breakdown
• Hermes 3 Llama 3.1 70B — full cost breakdown
• Llama 3.1 70B Instruct — full cost breakdown
• Llama 3.3 70B Instruct — full cost breakdown
• StableBeluga2 — full cost breakdown

Why no own-it math for the A100 80GB?

• We only publish own-it economics where we have a sourced, dated street price — none for this card yet, and we don't invent numbers.

Rent-price history (append-only daily log)

• RunPod: $1.39/hr on 2026-06-20 → $1.39/hr on 2026-07-02 (+0.0%). Logged daily; never back-filled.

Keep exploring

• All GPUs — rental rates compared
• Can I run it? Check any model against your hardware
• Free cost calculator — local vs rent vs API
• How we stay honest

Open the free Spanvero advisor → · GPU rates as of 2026-07-02. Honest, $0-markup — your own accounts, we never resell compute. © 2026 Cynosure LLC.