Qwen3.8-27B

· llama.cpp · 32K context · RTX 2080 Ti · 22 GB

Alibaba's 27B dense model from August 2026, and the strongest model that fits one consumer card. It thinks before it answers, calls tools reliably and reads images, which makes it the default for coding agents and long projects.

28 tok/sdecode

501 tok/sprefill

32Kcontext window

Tested on this cardOct 16, 2026

Run it

Follow the steps below to download and run this recipe. Omarchy Local AI lists the recipes it can launch on your hardware. The server then answers on http://localhost:8000/v1.

1 Download the weights

hf download unsloth/Qwen3.8-27B-GGUF Qwen3.8-27B-UD-Q4_K_M.gguf \
  --revision 4ca720788d1e01f1bff70c033e0d0028fd02e502 \
  --local-dir ~/models/Qwen3.8-27B-GGUF-4ca72078

2 Start the server

docker run --rm \
  --gpus all \
  -p 8000:8080 \
  --shm-size 1g \
  -e CUDA_DEVICE_ORDER=PCI_BUS_ID \
  -v ~/models/Qwen3.8-27B-GGUF-4ca72078:/models:ro \
  --entrypoint /app/llama-server \
  ghcr.io/ggml-org/llama.cpp:server-cuda12-b11146@sha256:52192a23c7b258044463aebba78826cdff39a7393b713edc313324b343a7b836 \
  --model /models/Qwen3.8-27B-UD-Q4_K_M.gguf \
  --alias Qwen3.8-27B \
  --host 0.0.0.0 \
  --port 8080 \
  --n-gpu-layers 999 \
  --split-mode none \
  --ctx-size 32768 \
  --parallel 1 \
  --flash-attn on \
  --cache-type-k q4_0 \
  --cache-type-v q4_0 \
  --jinja \
  --metrics \
  --no-mmproj \
  --fit off \
  --batch-size 512 \
  --ubatch-size 128 \
  --chat-template-kwargs '{"reasoning_effort":"medium"}'

What it passed

✓ loadLoads and serves within an hour

✓ chatAnswers a plain question and stops on its own

✓ reasoningThinks separately and gets 17 × 23 right

✓ toolsCalls a tool with the right arguments and uses the result

✓ contextRecalls a code buried in a prompt that fills 85% of the window

✓ speedDecodes at 15 tok/s or more

Passed all six checks on a real NVIDIA GeForce RTX 2080 Ti (22 GiB memory mod) on Oct 16, 2026.

Details

Weights: unsloth/Qwen3.8-27B-GGUF @ 4ca720788d ›
Image: ghcr.io/ggml-org/llama.cpp:server-cuda12-b11146@sha256:52192a23c7b258044463aebba78826cdff39a7393b713edc313324b343a7b836
Launch: llama.cpp-qwen3.8-27b-ud-q4-k-m-32k-cuda12 ›
Recipe file: registry/recipes/nvidia/rtx-2080-ti-22gb/qwen3.8-27b.llama.cpp.32k.json ›
Model released: Aug 5, 2026
Tested: owner, NVIDIA GeForce RTX 2080 Ti (22 GiB memory mod)