Workflows/Build a local AI agent with Qwen3.8 27B

Agents / WORKFLOW

Build a local AI agent with Qwen3.8 27B

Run Qwen3.8 with Ollama, connect Hermes Agent, and produce a source-checked local project review on your machine or a private rental.

Verified sourceSource checked 10/14/2026

LOCALRENTED GPU

Freshness 76 out of 100. Repository age: 71 days old, Aug 5, 2026. Measures age, not quality.

Popularity 95 out of 100. 7,363,968 downloads in 30 days; 17,749 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

Before you begin

Hardware

Short-context starting points for the complete Ollama package, runtime and tool exchange.

Machine	Qwen3.8 · 27B Q4	Underdog Saluki · 27B IQ2
NVIDIA GPU · 16 GB VRAM	Partial CPU offload likely; expect slower agent steps.	Capacity candidate at 8K context; confirm llama.cpp GPU offload and a real tool call.
NVIDIA GPU · 24 GB VRAM	Plausible full-GPU short-context start; check actual free VRAM.	Plenty of short-context memory for the 7.89 GB GGUF; tool quality still needs a run.
NVIDIA GPU · 32 GB VRAM	More headroom for the 18 GB weights and 8K context.	Plenty of memory for this 2-bit package; choose the official Q4 if quality matters more than size.
AMD Radeon · 24 GB VRAM	Ollama GPU support depends on the exact ROCm/Vulkan card and driver; test the backend before assuming full offload.	Capacity candidate if a matching llama.cpp Vulkan/ROCm backend works on this exact card.
Intel Arc · 24 GB VRAM	Check Ollama Intel backend support for the exact card; CPU offload can be slow.	Capacity candidate only with a working Intel llama.cpp GPU backend; otherwise CPU offload may be slow.
Apple Silicon Mac · 32 GB unified memory	Plausible short-context start with the official MLX package; monitor memory pressure.	Capacity candidate at 8K context; check Metal offload and memory pressure.
CPU only · 32 GB RAM	Can load with sufficient RAM but agent steps may be slow; start with a smaller model if needed.	The GGUF may load in RAM, but tool steps can be slow without GPU acceleration.
RunPod · NVIDIA GPU · 24 GB VRAM	Plausible rental start; keep the pod private and stop it afterward.	Capacity candidate; a larger rental can use the original Q4 package instead.

The package page documents 18 GB and tool support. These capacity bands are estimates, not YouRunAI benchmarks. Saluki is a community 2-bit GGUF; its quality and tool-call benchmarks are publisher-reported, while memory fit is estimated.

LOCAL AGENT · MAC · WINDOWS · LINUXSOURCE-LINKED SETUP

A private agent that uses your files.

Run the official Ollama package, verify tool calling, then connect Hermes to your private model and produce a checked project review. The probe is a prerequisite, not the final task.

Choose a package Run its commands Check the result

BEFORE YOU BEGIN

Choose your package

Select the weights you want. The instructions, downloads and settings change with your choice.

Save your machine in My Hardware to get an automatic starting choice. You can always choose any package yourself.

CURRENT SETUP

Qwen3.8 · 27B Q4 · official

Start at 8,192 tokens on a 24 GB GPU or 32 GB unified Mac; the 18 GB download needs extra runtime and KV-cache memory. Longer context raises memory use.

Freshness unavailable. Date pending.

Popularity unavailable. Stats pending.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

Check the date source

Popularity · adoption

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Scores as of Oct 15, 2026. Statistics check pending. Statistics are marked for refresh after 72 hours. These statistics are due for a refresh.Full scoring method

View weight source

THE WORKFLOW

Set up Qwen3.8 · 27B Q4 on your machine

Choose your computer first, then its GPU path. The instructions below update to match your selection.

CHOOSE YOUR SETUPWindows

Check the machine before downloading

Check 24 GB GPU VRAM or sufficient system RAM for offload free for the full model, runtime and a short context. This is a conservative capacity starting point, not a measured speed claim.

Exact Ollama package

Install and start Ollama

Download Ollama for Windows and open it. In PowerShell, confirm the app is running before the model download. Ollama manages the package files, so no manual model folder tree is needed.

Download Ollama for this operating system Official model package

Download the exact package and set a short context

In PowerShell, pull qwen3.8:27b-q4_K_M. Start with 8,192 tokens when connecting the agent; the published maximum context is not a safe default for every machine. The download is large and can take time.

Package identity and disk size

PowerShell

ollama pull qwen3.8:27b-q4_K_M
ollama show qwen3.8:27b-q4_K_M

Check model tool calling

In PowerShell, run the small read-only probe against qwen3.8:27b-q4_K_M. It must report a tool call; this only checks the model connection and is not the agent workflow outcome.

Download the connection check Ollama tool support and model package

PowerShell

py -m pip install openai
Invoke-WebRequest -Uri https://www.yourunai.com/workflow-files/private-file-agent.py -OutFile private-file-agent.py
py private-file-agent.py 'qwen3.8:27b-q4_K_M' http://127.0.0.1:11434/v1

Install and connect Hermes Agent

Install Hermes on your own Windows, Mac or Linux computer. Choose Custom endpoint in hermes model, enter http://127.0.0.1:11434/v1 and exact model ID qwen3.8:27b-q4_K_M, and start with 8,192 context. For RunPod, tunnel port 11434 over SSH so the same loopback URL works privately; do not publish Ollama's unauthenticated API.

Official Hermes installers Connect an Ollama/custom endpoint

Have the agent produce a useful result

Create a disposable folder containing a short project brief and a checklist with one missing backup step. Ask Hermes to read both, write review.md with a corrected checklist and the missing risk, and cite which local file supplied each fact. Review its requested file access and write before approval. This real file-based outcome, not the earlier read_notes probe, is the agent task.

Hermes agent and model setup

Inspect the artifact and close the service

Open review.md and check that Hermes actually used file tools, included the launch day and backup risk, and produced a useful corrected checklist. If the exact model/package fails at tool use, mark it unverified rather than treating a plain answer as success. On a rental, save the artifact and stop the pod.

SUCCESS CHECK · Qwen3.8 · 27B Q4

A source-checked review.md from Hermes

Hermes reads the disposable project files and writes a corrected checklist in review.md with the launch day and missing backup risk. Inspect the actual file and tool activity; the read_notes probe alone does not pass.

The optional Saluki compression is a community package, not a verified “uncensored” variant. Select it only if the saved memory matters, then require the guide’s real tool-call success check.

Back to setup steps

When it doesn’t go to plan

The full package does not fit or answers slowly.

Use the exact package size, leave runtime and context headroom, begin at 8K–16K context, and choose a larger machine or a smaller model if it still offloads heavily.

The agent returns text but no tool call.

Check the selected Ollama package has tool support, update Ollama, then retry the bounded script. Do not promote plain chat to a working agent path.

The client cannot connect to the local server.

Keep Ollama running, check http://127.0.0.1:11434/v1, and use an SSH tunnel for a rental. Never expose the unauthenticated port publicly.

REFERENCE LIBRARY

Sources and files

Original instructions, model files, and compatibility notes behind this setup.

4 SOURCES

01Official Ollama Qwen3.8 packages and tool supportollama.com 02Qwen publisher checkpointhuggingface.co 03Hermes custom endpoint setuphermes-agent.nousresearch.com 04Community Saluki GGUF, exact file and tool-call claimshuggingface.co

The model behind this workflow

Qwen3.8-27B

Keep exploring

Text

SETUP GUIDE

Qwen3.5 · 9B private chat setup

Source-backed package and platform-route plan for private local chat with Qwen3.5 · 9B. Preserves the official Ollama 9B package, a smaller 4B family fallback, and a clearly labeled community uncensored GGUF option.

Freshness 41 out of 100. Release age: 230 days old, Feb 27, 2026. Measures age, not quality.

Build a private coding assistant with Qwen3.8 27B

Run Qwen3.8 27B with Ollama, connect it to Cline in VS Code, and make one reviewable code change in a tiny local project.

Freshness 76 out of 100. Repository age: 71 days old, Aug 5, 2026. Measures age, not quality.

Arena Open Source Web coding: rank 10 of 55. Ranked model: qwen3.8-27b. Original model ranking, not a benchmark of this package. Export dated Oct 13, 2026. Source checked Oct 15, 2026. Human preference ranking, not hardware suitability.+3

SOFTWAREOllama + Visual Studio Code + Cline + Python

Create images locally with FLUX.2 Klein

Generate images from text prompts in ComfyUI with the fast distilled or more adjustable base 4B model. Save your results and reuse the visual workflow.

Freshness 35 out of 100. Release age: 273 days old, Jan 15, 2026. Measures age, not quality.

SOFTWAREComfyUI

LOCALRENTED GPU

Verified source