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.

Qwen3.8-27B-DSpine-b16

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

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

On your GPU

  • Qwen3.8-27B-DSpine-b16
Property
Overview
TaskChat
Parameters2B
Active parametersdense
Context length256K
Input → output
Released7 Nov 2026
LicenceApache 2.0
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈1.9 GB
VRAM at Q4≈1.9 GB
VRAM at Q8≈2.8 GB
VRAM at FP16≈4.6 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days5.6K
Likes276
Runs with
MLX
Ollama tag—
Architecture
ArchitectureDSpineDraftModel
Layers5
Attention / KV heads32 / 8
Vocabulary248 320
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.