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.

plamo-3-8b-fin-instruct

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

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

On your GPU

  • plamo-3-8b-fin-instruct
Property
Overview
TaskChat
Parameters8.5B
Active parametersdense
Context length256K
Input → output
Released8 Nov 2026
Licenceplamo-community-license
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈6.1 GB
VRAM at Q4≈6.1 GB
VRAM at Q8≈9.9 GB
VRAM at FP16≈18 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days983
Likes10
Runs with
Jan
KoboldCpp
llama.cpp
LM Studio
LocalAI
Ollama
Transformers
vLLM
Ollama tag—
Architecture
ArchitecturePlamo3ForCausalLM
Layers32
Attention / KV heads32 / 4
Vocabulary107 520
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.