Llama-3.1-Distilled

DeepMount00

Parameters

Downloads

—

Likes

—

Avg score

29.6

6 benchmarks

Weights

Open

Released

—

About

Llama-3.1-Distilled is a 8B-parameter open-weights model in the Llama family from DeepMount00. Benchmarked on 6 evals, averaging 29.6.

llama3

Benchmark scores · 6

avg 29.6 — higher is better

IFEvalOpen LLM LB · 2026-05

78.4

MMLU-ProOpen LLM LB · 2026-05

30.9

BIG-Bench HardOpen LLM LB · 2026-05

30.8

MATH Lvl 5Open LLM LB · 2026-05

20.3

MuSROpen LLM LB · 2026-05

10.1

GPQA DiamondOpen LLM LB · 2026-05

7.2

Details

FamilyLlama

Parameters8B

Licensellama3

WeightsOpen

Released—

History

Capability over time

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