The flagship 671B total / 37B active Mixture-of-Experts foundation model with Multi-head Latent Attention (MLA), matching closed frontier models under MIT license.
The biggest open-weight breakthrough in history. If you have 64GB-128GB unified memory or a dual-GPU node, it replaces your entire cloud API bill under MIT.
No cardLocalAPIOpen weightsHFPermissive
ILLUSTRATIVE PROMPT
Analyze the architectural latency trade-offs between Multi-Head Attention and Multi-head Latent Attention (MLA).
PREVIEW NOTE
A rigorous mathematical analysis comparing KV-cache memory consumption and matrix compression ratios.
Google's 100% Free AI research assistant with citation-backed document grounding and viral two-host Deep Dive audio podcast generation.
BASE ARCHITECTURE / Gemini 1.5 Pro Deep Grounding
SInstant Cloud Web Studio (0 GB VRAM • 100% Free · $0)
ℹTHE BRUTAL TRUTH
The best free research tool on the internet. Strict citation grounding makes hallucinations virtually impossible, and the audio overview feature is revolutionary.
No card
ILLUSTRATIVE PROMPT
Upload 5 scientific PDF papers on CRISPR gene editing and ask for contradictions between them.
PREVIEW NOTE
Structured synthesis comparing study methodologies with clickable direct citations.
Apex Intelligence's 35B MoE language model trained via recursive automated AI research agents. Specialized in computational science, robotics simulation, Claude Code agent workflows, and deep scientific reasoning.
BASE ARCHITECTURE / Apex-35B-V1.0 (Automated Research MoE Architecture)
ARuns well (79/100) • Q4_K_M (~47 tok/s • 9GB free)
ℹTHE BRUTAL TRUTH
Trained by AI agents to perform AI and scientific research. Because only 3B parameters are active per token, it runs like a 3B model while delivering the deep reasoning depth of a 35B architecture on 16GB GPUs.
No cardLocalAPIOpen weightsHFPermissive
ILLUSTRATIVE PROMPT
Formulate a robotics trajectory optimization algorithm with obstacle avoidance constraints.
PREVIEW NOTE
Rigorous mathematical formulation with typed Python simulation code.
Microsoft's synthetic-data trained 14B reasoning powerhouse. Outperforms many 70B models on math, STEM logic, and structured evaluation under MIT license.
BASE ARCHITECTURE / Phi-4 (14B dense)
SRuns well (85/100) • Q4_K_M (~78 tok/s • 15GB free)
ℹTHE BRUTAL TRUTH
A synthetic data triumph. If you need math, logic, or STEM reasoning on a 12GB card, Phi-4 crushes models twice its size under a pure MIT license.
No cardLocalAPIOpen weightsHFPermissive
ILLUSTRATIVE PROMPT
Prove by mathematical induction that 1 + 2 + ... + n = n(n + 1)/2 for all natural numbers n.
PREVIEW NOTE
A formal mathematical proof establishing the base case n=1 and the inductive step k -> k+1.
World-leading open mathematical reasoning model, scoring over 85% on MATH benchmarks. Specialized for scientific computation, equations, and formal proofs.
