Model benchmarks
LFM3-Omni-2B-Q4_K_M local LLM performance
As of November 2026, LFM3-Omni-2B-Q4_K_M runs at up to 150.8 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
2B
Peak speed
150.8 tok/s
Average speed
150.5 tok/s
Avg PP
2256.6 tok/s
Min memory
3.5 GB
Max context
131,072 tokens
Avg output / run
6,088 tokens
Avg runtime / run
1m 1s
Avg quality
36.6
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 | 34.2 | 36.6 | 39.0 |
| Agent Workflow | 66.3 | 68.0 | 69.7 |
| Code Generation | 0.9 | 1.7 | 2.4 |
| Role Play & Narrative | 30.6 | 38.3 | 46.0 |
| Research & Analysis | 35.8 | 38.5 | 41.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination LFM3-Omni-2B-Q4_K_M has been benchmarked on, ranked by peak token generation speed. Last updated November 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Advanced Micro Devices, Inc. [AMD/ATI] HawkPoint1 | llama.cpp | Q4_K_M | 150.8 tok/s | 150.5 tok/s | 3.5 GB | 131,072 tokens | 36.6 | 2 |
Benchmark runs
All 2 LFM3-Omni-2B-Q4_K_M runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is LFM3-Omni-2B-Q4_K_M good for agentic (tool-using) tasks?
- In our benchmarks, LFM3-Omni-2B-Q4_K_M scores 68.0/100 for agentic workflows. It runs at about 150.5 tok/s, so if you want more speed, unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M is faster (~246.8 tok/s) and still scores well for agentic workflows (80.6/100).
- How fast is LFM3-Omni-2B-Q4_K_M for local inference?
- Across 2 community benchmark runs, LFM3-Omni-2B-Q4_K_M reaches up to 150.8 tok/s and averages 150.5 tok/s, with the fastest results on Advanced Micro Devices, Inc. [AMD/ATI] HawkPoint1.
- How much memory does LFM3-Omni-2B-Q4_K_M need?
- The leanest observed configuration used about 3.5 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run LFM3-Omni-2B-Q4_K_M?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.