Ollama benchmark
Continuous, automated speed tests for every Ollama Cloud model. One streaming request per model every ~10 minutes. No cherry-picked results — just raw measurements from outside Ollama's network.
Top 10 fastest Ollama Cloud models right now
| Rank | Model | TPS now | TPS 24h avg | TTFT | Reliability |
|---|---|---|---|---|---|
| #1 | GPT-OSS 120B | 362.6 | 333.9 | 338ms | 100% |
| #2 | Gemma4 31B | 291.4 | 235.3 | 291ms | 100% |
| #3 | GPT-OSS 120B | 290.8 | 290.9 | 362ms | 100% |
| #4 | Gemma4 31B | 289.1 | 220.1 | 325ms | 100% |
| #5 | GLM 5.3 Flash | 266.6 | 217.8 | 497ms | 100% |
| #6 | MiMo V2.6 Pro | 263.9 | 236.6 | 697ms | 100% |
| #7 | MiniMax M3 | 223.6 | 120.7 | 755ms | 100% |
| #8 | DeepSeek V4.1 Flash 1017 | 216.7 | 211.4 | 584ms | 100% |
| #9 | MiMo V2.6 Flash | 213.1 | 256.7 | 309ms | 100% |
| #10 | Nemotron 3 Super | 212.9 | 126.3 | 378ms | 100% |
What the Ollama benchmark measures
Each benchmark run sends a single streaming chat-completion request
to the Ollama Cloud API endpoint. The model is prompted to write a
400-word prose explanation of HTTP request routing, with a
max_tokens cap of 300.
- TPS — tokens per second
- Generation throughput: output tokens divided by the time between first and last token. Excludes TTFT so TPS reflects pure decode speed, not queue or prompt-processing delay.
- TTFT — time to first token
- Milliseconds from request dispatch to the first content chunk in the stream. Captures network round-trip plus the provider's prompt-processing latency.
- Reliability
- Percentage of benchmark runs that succeeded in the last 24 hours. Failures are classified as auth, rate_limit, server, timeout, network, or malformed.
Benchmark cadence and fairness
The worker uses a priority queue that always picks the most-overdue (provider, model) pair, targeting a ~10-minute interval per model. Benchmarks run sequentially — one request at a time — mirroring realistic single-client usage.
We benchmark on the Ollama Cloud premium plan. This gives full catalog access including models behind the paywall. Speed numbers reflect premium-tier infrastructure, not free-tier which may be slower under load.
How to read the numbers
- TPS is relative, not absolute. The same model can vary 20–30% across hours depending on provider load and time of day. Use the 24h average for a more stable comparison.
- TTFT matters for interactive use. A model with high TPS but 3 s TTFT feels slow in a chat interface. The leaderboard sorts by latest TPS by default — sort by TTFT to optimise for responsiveness.
- Reliability is often the deciding factor. A model that returns errors 30% of the time needs retry logic in production. Filter for ≥90% reliability for production workloads.