Ollama / Ollama

Ollama: Pull Fails with EOF Error for Large Models on aarch64 (DGX Spark / GB10)

Fix Ollama pull failing with EOF error when downloading large models on ARM64/aarch64 systems Includes evidence for Ollama troubleshooting demand.

Source-backed Last updated May 13, 2026 1 source Needs local verification

Category: Ollama
Error signature: Error: EOF during ollama pull gpt-oss-safeguard:120b on aarch64
Quick fix: Verify the model name, local service connectivity, and network access before retrying the model pull.
Updated: May 13, 2026
Verification status: Source-backed
Evidence: 1 public source URL

Before you change production

This page includes public source URLs in the imported troubleshooting record. Compare those references with your version and environment before applying changes.

Reproduce the smallest failing action and save non-secret logs before changing configuration.
Check versions for Ollama, related SDKs, package managers, CI runners, and hosting providers.
Change one setting or dependency at a time, then rerun the same failing command or request.
Avoid destructive commands, credential rotation, billing changes, or security relaxations without a rollback plan.

What this error means

Error: EOF during ollama pull gpt-oss-safeguard:120b on aarch64 is a Ollama failure pattern reported for developers trying to fix ollama pull failing with eof error when downloading large models on arm64/aarch64 systems. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

Reproduces on Ollama 0.23.2 and 0.23.3-rc1, including official Docker images. Issue is model-specific (120b variant), not registry/network. aarch64 enterprise hardware (DGX Spark) audience with high commercial intent.

Common causes

On NVIDIA DGX Spark / GB10 (aarch64), pulling the 20GB gpt-oss-safeguard:120b model fails with Error: EOF. The smaller 20b sibling and unrelated models pull normally on the same host. Affects enterprise AI/ML engineers using DGX hardware with Ollama.
Reproduces on Ollama 0.23.2 and 0.23.3-rc1, including official Docker images. Issue is model-specific (120b variant), not registry/network. aarch64 enterprise hardware (DGX Spark) audience with high commercial intent.

Quick fixes

Confirm the exact error signature matches Error: EOF during ollama pull gpt-oss-safeguard:120b on aarch64.
Check the Ollama account, local tool state, and provider configuration involved in the failing workflow.
Verify the model name, local service connectivity, and network access before retrying the model pull.

Platform/tool-specific checks

Verify the command, editor, extension, or API client that produced the error.
Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

Capture the exact error message and the command, editor action, or request that triggered it.
Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
Review the source evidence below and compare it with your environment.
Apply one change at a time and rerun the smallest failing action.
Keep the working fix documented for the team or deployment environment.

How to prevent it

Keep provider/tool configuration documented.
Record non-secret diagnostics such as tool version, provider name, model name, and command path.
Add a lightweight check before CI or production workflows depend on the tool.

Diagnostic flow for this page

Match Error: EOF during ollama pull gpt-oss-safeguard:120b on aarch64 exactly before applying the quick fix.
Compare the failing environment with Ollama versions, account scope, provider settings, and deployment context.
Check the listed common causes in order, starting with the cause that best matches your logs.
Use the evidence status below to decide whether to confirm against public sources or official documentation.
Apply one reversible change, rerun the smallest failing action, and keep rollback notes.

FAQ

What does Error: EOF during ollama pull gpt-oss-safeguard:120b on aarch64 mean in Ollama?

Error: EOF during ollama pull gpt-oss-safeguard:120b on aarch64 indicates the workflow described by "Ollama: Pull Fails with EOF Error for Large Models on aarch64 (DGX Spark / GB10)" failed in a Ollama context. Start by confirming the exact signature and the component that emitted it.

What should I check first for Error: EOF during ollama pull gpt-oss-safeguard:120b on aarch64?

Check whether this cause matches your environment: On NVIDIA DGX Spark / GB10 (aarch64), pulling the 20GB gpt-oss-safeguard:120b model fails with Error: EOF. The smaller 20b sibling and unrelated models pull normally on the same host. Affects enterprise AI/ML engineers using DGX hardware with Ollama.

Is the Error: EOF during ollama pull gpt-oss-safeguard:120b on aarch64 guidance source-backed?

The "Ollama: Pull Fails with EOF Error for Large Models on aarch64 (DGX Spark / GB10)" page is labeled source-backed. It has 1 public source URL from github.com, so use that evidence status when deciding how much additional verification you need.

When should I avoid the quick fix for Error: EOF during ollama pull gpt-oss-safeguard:120b on aarch64?

For "Ollama: Pull Fails with EOF Error for Large Models on aarch64 (DGX Spark / GB10)", avoid applying "Verify the model name, local service connectivity, and network access before retrying the model pull." when the error text differs, the affected version or provider is different, or the change would touch credentials, billing, DNS, production deploy settings, or irreversible data.

What should I collect before debugging Error: EOF during ollama pull gpt-oss-safeguard:120b on aarch64?

For "Ollama: Pull Fails with EOF Error for Large Models on aarch64 (DGX Spark / GB10)", collect the failing Ollama command or request, non-secret configuration, versions, timestamps, request IDs when available, and the smallest reproduction that still triggers the signature.