Model benchmarks
stablelm-2-zephyr-1_6b local LLM performance
As of October 2026, stablelm-2-zephyr-1_6b runs at up to 56.4 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
6B
Peak speed
56.4 tok/s
Average speed
56.3 tok/s
Avg PP
2124.7 tok/s
Min memory
2.7 GB
Max context
16,384 tokens
Avg output / run
2,480 tokens
Avg runtime / run
49s
Avg quality
17.0
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 | 13.3 | 17.0 | 20.7 |
| Agent Workflow | 15.6 | 23.7 | 31.8 |
| Code Generation | 2.7 | 4.4 | 6.1 |
| Role Play & Narrative | 13.4 | 19.8 | 26.1 |
| Research & Analysis | 18.7 | 20.0 | 21.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination stablelm-2-zephyr-1_6b 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 | 56.4 tok/s | 56.3 tok/s | 2.7 GB | 16,384 tokens | 17.0 | 2 |
Benchmark runs
All 2 stablelm-2-zephyr-1_6b runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is stablelm-2-zephyr-1_6b good for coding?
- In our benchmarks, stablelm-2-zephyr-1_6b scores 4.4/100 for coding. It runs at about 56.3 tok/s, so if you want more speed, nvidia/Qwen3.8-27B-NVFP4 is faster (~75.5 tok/s) and still scores well for coding (83.5/100).
- Is stablelm-2-zephyr-1_6b good for agentic (tool-using) tasks?
- In our benchmarks, stablelm-2-zephyr-1_6b scores 23.7/100 for agentic workflows. It runs at about 56.3 tok/s, so if you want more speed, Nex-N2.5-mini-APEX-Mini is faster (~88.2 tok/s) and still scores well for agentic workflows (91.3/100).
- How fast is stablelm-2-zephyr-1_6b for local inference?
- Across 2 community benchmark runs, stablelm-2-zephyr-1_6b reaches up to 56.4 tok/s and averages 56.3 tok/s, with the fastest results on NVIDIA GeForce RTX 2050.
- How much memory does stablelm-2-zephyr-1_6b need?
- The leanest observed configuration used about 2.7 GB of memory (quantizations tested: Q8_0).
- Which tools have been used to run stablelm-2-zephyr-1_6b?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.