Model benchmarks
tinyllama-1.1b-chat-v1.0 local LLM performance
As of October 2026, tinyllama-1.1b-chat-v1.0 runs at up to 87.1 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
1.1B
Peak speed
87.1 tok/s
Average speed
86.7 tok/s
Avg PP
3748.3 tok/s
Min memory
3.6 GB
Max context
16,384 tokens
Avg output / run
3,602 tokens
Avg runtime / run
46s
Avg quality
10.2
Benchmark runs
2
GPUs tested
1
Quality by task
Average LLM-judged quality (0–100) with the run-to-run spread shown as a P5–P95 band, overall and for each benchmark task, across all 2 runs. The low and high columns show how much the judge’s score varies between runs, and need at least two runs to display.
| Task | P5 (low) | Avg | P95 (high) |
|---|---|---|---|
| Overall | 9.2 | 10.2 | 11.3 |
| Agent Workflow | 9.9 | 12.8 | 15.7 |
| Code Generation | 5.0 | 6.2 | 7.4 |
| Role Play & Narrative | 9.3 | 11.0 | 12.8 |
| Research & Analysis | 10.1 | 10.9 | 11.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination tinyllama-1.1b-chat-v1.0 has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 2050 | LM Studio | Q8_0 | 87.1 tok/s | 86.7 tok/s | 3.6 GB | 16,384 tokens | 10.2 | 2 |
Benchmark runs
All 2 tinyllama-1.1b-chat-v1.0 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is tinyllama-1.1b-chat-v1.0 good for coding?
- In our benchmarks, tinyllama-1.1b-chat-v1.0 scores 6.2/100 for coding. It runs at about 86.7 tok/s, so if you want more speed, Ornith-1.5-35B-A3B.APEX-I-NanoPlus is faster (~110.5 tok/s) and still scores well for coding (81.1/100).
- Is tinyllama-1.1b-chat-v1.0 good for agentic (tool-using) tasks?
- In our benchmarks, tinyllama-1.1b-chat-v1.0 scores 12.8/100 for agentic workflows. It runs at about 86.7 tok/s, so if you want more speed, cyber-tiel-coder-35b-a3b-mtp is faster (~115.9 tok/s) and still scores well for agentic workflows (86.4/100).
- How fast is tinyllama-1.1b-chat-v1.0 for local inference?
- Across 2 community benchmark runs, tinyllama-1.1b-chat-v1.0 reaches up to 87.1 tok/s and averages 86.7 tok/s, with the fastest results on NVIDIA GeForce RTX 2050.
- How much memory does tinyllama-1.1b-chat-v1.0 need?
- The leanest observed configuration used about 3.6 GB of memory (quantizations tested: Q8_0).
- Which tools have been used to run tinyllama-1.1b-chat-v1.0?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.