selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

Nex-N2.6

Side-by-side specs, memory needs, licence, runtimes and benchmarks. Add up to 4 models.

--vram
any
--gpus
--quant
--add

On your GPU

  • Nex-N2.6
Property
Overview
TaskVision
Parameters321B
Active parameters18.3B
Context length1M
Input → output
Released10 Nov 2026
LicenceApache 2.0
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈213 GB
VRAM at Q4≈213 GB
VRAM at Q8≈357 GB
VRAM at FP16≈651 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days1.5K
Likes164
Runs with
Jan
KoboldCpp
llama.cpp
LM Studio
LocalAI
MLX
Ollama
SGLang
Transformers
vLLM
Ollama tag—
Architecture
ArchitectureGlm5NextForConditionalGeneration
Layers45
Attention / KV heads64 / 64
Vocabulary154 880
Weights dtypebfloat16
GGUF availableyes

Keep comparing

Memory figures are estimates for an 8K context at the chosen quantisation (Q4_K_M for LLMs by default). Speeds are rough, memory-bound estimates. Self-reported benchmark scores come from the model authors.