Model benchmarks
laguna-xs-2.1 local LLM performance
As of July 2026, laguna-xs-2.1 runs at up to 37.2 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
LM Studio
Model size
Unknown
Peak speed
37.2 tok/s
Average speed
27.4 tok/s
Min memory
18.9 GB
Max context
65,536 tokens
Avg quality
62.0
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 | 55.6 | 62.0 | 68.5 |
| Agent Workflow | 78.9 | 81.9 | 84.8 |
| Code Generation | 2.9 | 29.0 | 55.1 |
| Role Play & Narrative | 66.3 | 70.8 | 75.3 |
| Research & Analysis | 65.1 | 66.5 | 67.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination laguna-xs-2.1 has been benchmarked on, ranked by peak token generation speed. Last updated July 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4070 Ti SUPER | LM Studio | — | 37.2 tok/s | 27.4 tok/s | 18.9 GB | 65,536 tokens | 62.0 | 2 |
Frequently asked questions
- Is laguna-xs-2.1 good for coding?
- In our benchmarks, laguna-xs-2.1 scores 29.0/100 for coding. It runs at about 27.4 tok/s, so if you want more speed, K2-Horizon-MoVA-36B-A4B-MLX-4bit is faster (~48.8 tok/s) and still scores well for coding (85.3/100).
- Is laguna-xs-2.1 good for agentic (tool-using) tasks?
- In our benchmarks, laguna-xs-2.1 scores 81.9/100 for agentic workflows. It runs at about 27.4 tok/s, so if you want more speed, muse-glimmer:latest is faster (~34.5 tok/s) and still scores well for agentic workflows (93.0/100).
- How fast is laguna-xs-2.1 for local inference?
- Across 2 community benchmark runs, laguna-xs-2.1 reaches up to 37.2 tok/s and averages 27.4 tok/s, with the fastest results on NVIDIA GeForce RTX 4070 Ti SUPER.
- How much memory does laguna-xs-2.1 need?
- The leanest observed configuration used about 18.9 GB of memory.
- Which tools have been used to run laguna-xs-2.1?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.