Large (34–80B) AI models

All 25 open large models. Top quality that still fits a single big rented GPU. The honest, $0-markup cost to run each — free on your machine, a rented GPU, or your own API key.

Llama 3.1 70B Instruct — 70B, Meta · $0.40/1M API
Llama 3.3 70B Instruct — 70B, Meta · $0.66/1M API est.
Mixtral 8x7B Instruct — 46.7B, Mistral AI · $0.24/1M API last-known
Qwen2.5 72B Instruct — 72B, Alibaba · $0.68/1M API est.
dolphin 2.9.1 yi 1.5 34b — 34.4B, dphn · $0.38/1M API est.
NVIDIA Nemotron 3 Super 120B A12B NVFP4 — 67.2B, nvidia · $0.64/1M API est.
Qwen3 Coder Next — 79.7B, Qwen · $0.74/1M API est.
Llama 3 3 Nemotron Super 49B v1 5 — 49.9B, nvidia · $0.50/1M API est.
Qwen2.5 72B Instruct abliterated — 72.7B, huihui-ai · $0.68/1M API est.
Yi-1.5-34B-Chat — 34.4B, 01.AI · $0.38/1M API est.
Meta Llama 3 70B — 70.6B, meta-llama · $0.66/1M API est.
Karnak 40B v1.0 — 40.7B, Applied-Innovation-Center · $0.43/1M API est.
Llama 3 3 Nemotron Super 49B v1 — 49.9B, nvidia · $0.50/1M API est.
Phi 3.5 MoE instruct — 41.9B, microsoft · $0.44/1M API est.
Meta Llama 3.1 70B Instruct quantized.w4a16 — 70.6B, RedHatAI · $0.66/1M API est.
StableBeluga2 — 69B, petals-team · $0.65/1M API est.
Kimi Linear 48B A3B Instruct — 49.1B, moonshotai · $0.49/1M API est.
DeepSeek R1 Distill Llama 70B — 70.6B, deepseek-ai · $0.66/1M API est.
Llama 2 70b chat hf — 69B, meta-llama · $0.65/1M API est.
Llama 3.1 70B — 70.6B, meta-llama · $0.66/1M API est.
Hermes 3 Llama 3.1 70B — 70.6B, NousResearch · $0.66/1M API est.
Seed OSS 36B Instruct — 36.2B, ByteDance-Seed · $0.39/1M API est.
Qwen3.5 122B A10B heretic MTP NVFP4 — 73.7B, OptimizeLLM · $0.69/1M API est.
Huihui Qwen3.6 35B A3B Claude 4.7 Opus abliterated — 36B, huihui-ai · $0.39/1M API est.
Qwen3.5 122B A10B NVFP4 — 64.6B, nvidia · $0.62/1M API est.

Other sizes

Flagship (80B+) · Medium (14–34B) · Small (4–14B) · Tiny (under 4B) · All models

Compare → · Cost calculator →