Model benchmarks
Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M local LLM performance
As of October 2026, Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M runs at up to 70.0 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
8B
Peak speed
70.0 tok/s
Average speed
62.5 tok/s
Avg PP
347.9 tok/s
Min memory
10.4 GB
Max context
16,384 tokens
Avg output / run
5,170 tokens
Avg runtime / run
1m 31s
Avg quality
52.6
Benchmark runs
3
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 3 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 | 51.0 | 52.6 | 54.4 |
| Agent Workflow | 41.4 | 57.9 | 70.3 |
| Code Generation | 28.7 | 40.0 | 47.6 |
| Role Play & Narrative | 38.6 | 55.6 | 66.6 |
| Research & Analysis | 52.7 | 56.8 | 62.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M 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 2080 Ti | llama.cpp | Q4_K_M | 70.0 tok/s | 62.5 tok/s | 10.4 GB | 16,384 tokens | 52.6 | 3 |
Benchmark runs
All 3 Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M good for coding?
- In our benchmarks, Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M scores 40.0/100 for coding. It runs at about 62.5 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 Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M good for agentic (tool-using) tasks?
- In our benchmarks, Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M scores 57.9/100 for agentic workflows. It runs at about 62.5 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 Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M for local inference?
- Across 3 community benchmark runs, Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M reaches up to 70.0 tok/s and averages 62.5 tok/s, with the fastest results on NVIDIA GeForce RTX 2080 Ti.
- How much memory does Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M need?
- The leanest observed configuration used about 10.4 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.