Skip to content

GPQA Resources from D-Central

AI

Qwen 3

Alibaba’s May 2025 release — first open family with hybrid reasoning (toggle-able chain of thought), Apache 2.0 across all sizes.

AI

Llama 4 (Scout/Maverick)

Meta’s April 2025 MoE-and-multimodal release, headlined by Scout’s 10M-token context window. The pre-announced Behemoth frontier model never shipped — Meta’s next frontier release (Muse Spark, April 2026) went closed-weight.

AI

Gemma 3

Google DeepMind’s March 2025 Gemma family — vision-capable (4B+), 128K context, with official quantization-aware 4-bit variants.

AI

Mistral Small 3

Mistral AI’s January 2025 24B model — Apache 2.0, competitive with Llama 3.3 70B, fits on a single 24GB GPU.

AI

DeepSeek R1

DeepSeek’s January 2025 reasoning model — frontier chain-of-thought quality, plus six MIT-licensed distills from 1.5B to 70B.

AI

DeepSeek V3

DeepSeek’s December 2024 frontier-scale MoE — 671B total, 37B active, trained for ~$5.6M in compute.

AI

Phi-4

Microsoft Research’s December 2024 Phi-4 — a 14B dense MIT-licensed model punching well above its weight on math and reasoning.

AI

Llama 3.3

A single 70B model released December 2024, closing most of the gap to Llama 3.1 405B through improved post-training alone.

AI

Llama 3.2

Meta’s September 2024 Llama release added edge sizes (1B/3B) and the first open-weight Llama vision models (11B/90B).

AI

Qwen 2.5

Alibaba’s September 2024 Qwen family spans 0.5B to 72B, plus coding and math specialists — mostly Apache 2.0.

IA

Llama 3.1

Meta’s flagship 2024 open-weight LLM family — 8B, 70B, and 405B parameters with 128K context. The 405B was the first open-weight model at true frontier scale.

AI

Gemma 2

Google DeepMind’s June 2024 lightweight open model family — 2B, 9B, and 27B with interleaved local/global attention.

Related products, repair, and setup paths

Last reviewed April 16, 2026.