InternScience

Nex N2 Mini

Nex N2 Mini is an open-weights model by InternScience. It holds an Intelligence score of 71.3 on the local.ai leaderboard (2026-08 snapshot).

open weights
71.3
local.ai Intelligence
Parameters
undisclosed
Benchmarks (local.ai snapshot)
τ²-bench
85%
GAIA
79%
GDPval
64%
HuggingFace metadata · updated 2026-06-11
repo
nex-agi/Nex-N2-mini
license
apache-2.0
downloads
1,716
likes
295

Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.

Does it fit your hardware?

Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.

Params not disclosed — no size estimate.

Actual files on HuggingFace

FileSize
model-00006-of-00016.safetensors4.64 GB
model-00009-of-00016.safetensors4.64 GB
model-00012-of-00016.safetensors4.64 GB
model-00015-of-00016.safetensors4.64 GB
model-00003-of-00016.safetensors4.64 GB
model-00001-of-00016.safetensors4.42 GB
GGUF: mudler/Nex-N2-mini-APEX-GGUF · 10,182 downloads
FileSize
Nex-N2-mini-APEX-Balanced.gguf23.53 GBdownload
Nex-N2-mini-APEX-Compact.gguf15.40 GBdownload
Nex-N2-mini-APEX-I-Balanced.gguf23.53 GBdownload
Nex-N2-mini-APEX-I-Compact.gguf15.40 GBdownload
Nex-N2-mini-APEX-I-Mini.gguf12.54 GBdownload
Nex-N2-mini-APEX-I-Quality.gguf21.25 GBdownload
Nex-N2-mini-APEX-Quality.gguf21.25 GBdownload
mmproj.gguf0.84 GBdownload
GGUF: bartowski/nex-agi_Nex-N2-mini-GGUF · 6,516 downloads
FileSize
mmproj-nex-agi_Nex-N2-mini-bf16.gguf0.84 GBdownload
mmproj-nex-agi_Nex-N2-mini-f16.gguf0.84 GBdownload
nex-agi_Nex-N2-mini-IQ2_M.gguf11.24 GBdownload
nex-agi_Nex-N2-mini-IQ2_S.gguf10.25 GBdownload
nex-agi_Nex-N2-mini-IQ2_XS.gguf10.06 GBdownload
nex-agi_Nex-N2-mini-IQ2_XXS.gguf9.11 GBdownload
nex-agi_Nex-N2-mini-IQ3_M.gguf15.74 GBdownload
nex-agi_Nex-N2-mini-IQ3_XS.gguf15.10 GBdownload
nex-agi_Nex-N2-mini-IQ3_XXS.gguf13.85 GBdownload
nex-agi_Nex-N2-mini-IQ4_NL.gguf18.50 GBdownload
nex-agi_Nex-N2-mini-IQ4_XS.gguf17.51 GBdownload
nex-agi_Nex-N2-mini-Q2_K.gguf11.75 GBdownload

What you save self-hosting this model

Uses the model's own API price when it exists; otherwise the closest commercial equivalent.

Waiting for hardware detection…

RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.