Can Used NVIDIA RTX 3070 8GB run Llama, Qwen & DeepSeek? 183 models that fit

183 of the 396 models in the Spanvero catalog fit Used NVIDIA RTX 3070 8GB's 8 GB VRAM (at a sensible quant, 16k context). For each: run it locally ($0 compute + electricity), rent an equivalent GPU ($0 markup, as of 2026-07-02), or pay per-token via your own API key (as of 2026-07-06).

Three honest ways to run each model on Used NVIDIA RTX 3070 8GB

• Run it locally: $0 in compute — you pay only electricity (~220 W under load on this card). Local is real money, never a fake "$0".
• Rent an equivalent GPU: from a $0-markup vendor rate (as of 2026-07-02) — you rent on your own account and pay the vendor directly; we never resell compute.
• Skip the box: run the same model through your own API key, paying per million tokens (prices as of 2026-07-06).

What fits Used NVIDIA RTX 3070 8GB (8 GB VRAM)

• 183 of the 396 notable models in the Spanvero catalog fit Used NVIDIA RTX 3070 8GB at a sensible quant (context capped at 16k for the estimate). Most capable first:
• internlm3 8b instruct (internlm, 8.8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.276/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.17/1M via your own API key (size estimate).
• Nemotron Labs Diffusion 8B Base (nvidia, 8.5B) — needs ~7 GB at Q4_K_M: run it locally for $0 compute + ~$0.2684/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.17/1M via your own API key (size estimate).
• LFM2.5 8B A1B (LiquidAI, 8.5B) — needs ~7 GB at Q4_K_M: run it locally for $0 compute + ~$0.2684/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.17/1M via your own API key (size estimate).
• LFM2 8B A1B (LiquidAI, 8.3B) — needs ~7 GB at Q4_K_M: run it locally for $0 compute + ~$0.2634/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.17/1M via your own API key (size estimate).
• MiniCPM4.1 8B (openbmb, 8.2B) — needs ~7 GB at Q4_K_M: run it locally for $0 compute + ~$0.2608/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.17/1M via your own API key (size estimate).
• granite 3.0 8b instruct (ibm-granite, 8.2B) — needs ~7 GB at Q4_K_M: run it locally for $0 compute + ~$0.2608/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.17/1M via your own API key (size estimate).
• Llama 3.1 8B Instruct (Meta, 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.03/1M via your own API key.
• Qwen2-VL 7B Instruct (Alibaba, 8B) — needs ~7 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• Hermes 3 — Llama 3.1 8B (Nous Research, 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• Llama 3.1 8B Instruct (Abliterated) (mlabonne (community), 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• LLaDA 8B Instruct (GSAI-ML, 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• Dolphin 3.0 — Llama 3.1 8B (Cognitive Computations, 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• DeepSeek R1 Distill Llama 8B (deepseek-ai, 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• saiga llama3 8b (IlyaGusev, 8B) — needs ~7 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• Meta Llama 3.1 8B Instruct (unsloth, 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• LLaDA 1.5 (GSAI-ML, 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• Meta Llama 3 8B Instruct (NousResearch, 8B) — needs ~7 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• Meta Llama 3.1 8B Instruct (NousResearch, 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• Llama 3.1 8B Instruct (unsloth, 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).
• LLaDA 8B Base (GSAI-ML, 8B) — needs ~8 GB at Q4_K_M: run it locally for $0 compute + ~$0.2557/1M in electricity, rent NVIDIA RTX 3060 12GB from $0.06/hr ($0 markup), or ~$0.16/1M via your own API key (size estimate).

• internlm3 8b instruct — full cost breakdown
• Nemotron Labs Diffusion 8B Base — full cost breakdown
• LFM2.5 8B A1B — full cost breakdown
• LFM2 8B A1B — full cost breakdown
• MiniCPM4.1 8B — full cost breakdown
• granite 3.0 8b instruct — full cost breakdown
• Llama 3.1 8B Instruct — full cost breakdown
• Qwen2-VL 7B Instruct — full cost breakdown
• Hermes 3 — Llama 3.1 8B — full cost breakdown
• Llama 3.1 8B Instruct (Abliterated) — full cost breakdown
• LLaDA 8B Instruct — full cost breakdown
• Dolphin 3.0 — Llama 3.1 8B — full cost breakdown
• DeepSeek R1 Distill Llama 8B — full cost breakdown
• saiga llama3 8b — full cost breakdown
• Meta Llama 3.1 8B Instruct — full cost breakdown
• LLaDA 1.5 — full cost breakdown
• Meta Llama 3 8B Instruct — full cost breakdown
• Meta Llama 3.1 8B Instruct — full cost breakdown
• Llama 3.1 8B Instruct — full cost breakdown
• LLaDA 8B Base — full cost breakdown

The honest cost of owning Used NVIDIA RTX 3070 8GB

• Street price $228.00 (as of 2026-07-08; BestValueGPU eBay used-price tracker, Jun 2026 (~$228, reading dated Jun 18 2026)) — amortized over 3 years that's ~$0.2082/day whether or not you're generating.
• Electricity: ~220 W under sustained inference at $0.1883/kWh (EIA Electric Power Monthly Table 5.6.A — U.S. residential average, Apr 2026, as of 2026-07-02) — the per-1M-token figures above already include this at each model's speed.
• Straight talk: for the small models a 8 GB VRAM box runs, hosted APIs are often cheaper per token. Own local for privacy, offline use, and unlimited runs — not to save money on tokens.

Too big for Used NVIDIA RTX 3070 8GB — rent or use an API instead

• These need more than the 8 GB VRAM on this card. Closest first — you can still run them on a rented GPU ($0 markup) or via your own API key:
• Mellum2 12B A2.5B Thinking (JetBrains, 12.1B) — needs ~9 GB; rent NVIDIA RTX 3060 12GB from $0.06/hr, or ~$0.20/1M via your own API key (size estimate).
• Mellum2 12B A2.5B Base (JetBrains, 12.1B) — needs ~9 GB; rent NVIDIA RTX 3060 12GB from $0.06/hr, or ~$0.20/1M via your own API key (size estimate).
• gemma 2 9b it (unsloth, 9.2B) — needs ~9 GB; rent NVIDIA RTX 3060 12GB from $0.06/hr, or ~$0.17/1M via your own API key (size estimate).
• Gemma 2 9B Instruct (Google, 9B) — needs ~9 GB; rent NVIDIA RTX 3060 12GB from $0.06/hr, or ~$0.06/1M via your own API key (last-known).
• granite 4.1 8b (ibm-granite, 8.8B) — needs ~9 GB; rent NVIDIA RTX 3060 12GB from $0.06/hr, or ~$0.08/1M via your own API key.
• llm jp 4 8b thinking (llm-jp, 8.6B) — needs ~9 GB; rent NVIDIA RTX 3060 12GB from $0.06/hr, or ~$0.17/1M via your own API key (size estimate).

Keep exploring

• Check a different GPU or Mac
• All GPUs — rental rates compared
• Free cost calculator — local vs rent vs API
• All models — the real cost to run each
• How we stay honest

Open the free Spanvero advisor → · GPU rates as of 2026-07-02, API prices as of 2026-07-06. Honest, $0-markup — your own accounts, we never resell compute. © 2026 Cynosure LLC.