Hermes 4 70B

NousResearch · released 2025-08-26 · llama3 license

Hermes 4 70B is Nous Research's hybrid-reasoning fine-tune of Llama-3.1-70B (Aug 2025): MATH-500 95.5, AIME25 67.5, GPQA 66.1, LiveCodeBench 50.5 (reasoning mode). Artificial Analysis scores its non-reasoning mode 13.

Key specs

TypeLocal open-weight
Parameters70.55B total
Architecturellama
Context window131K tokens
Knowledge cutoff2024-08-31
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond66.1%
SWE-bench Verified
AIME67.5%
MMLU-Pro80.7%
BFCL v3 (tool use)
Composite score7.2
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M42.4 GB40.9 GB131K

Strengths & weaknesses

Strengths: Strong reasoning-mode math (MATH-500 95.5) for a 70B dense model; High steerability / low refusals; Faster and cheaper than average for its size

Weaknesses: Below-average overall intelligence vs same-size peers (AA index 13); Restrictive Llama license; 128K context