Llama-TI-8B-Instruct

fluently-lm

Parameters

Downloads

—

Likes

—

Avg score

29.7

6 benchmarks

Weights

Open

Released

—

About

Llama-TI-8B-Instruct is a 8B-parameter open-weights model in the Llama family from fluently-lm. Benchmarked on 6 evals, averaging 29.7.

apache-2.0

Benchmark scores · 6

avg 29.7 — higher is better

IFEvalOpen LLM LB · 2026-05

77.2

BIG-Bench HardOpen LLM LB · 2026-05

32.3

MMLU-ProOpen LLM LB · 2026-05

30.3

MATH Lvl 5Open LLM LB · 2026-05

23.0

MuSROpen LLM LB · 2026-05

9.2

GPQA DiamondOpen LLM LB · 2026-05

6.0

Details

FamilyLlama

Parameters8B

Licenseapache-2.0

WeightsOpen

Released—

History

Capability over time

Append-only ledger — every observed change to this model's numbers.