Model benchmarks
strata_ud-q4 local LLM performance
As of November 2026, strata_ud-q4 runs at up to 59.4 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
59.4 tok/s
Average speed
59.0 tok/s
Avg PP
232.3 tok/s
Min memory
124.0 GB
Max context
196,608 tokens
Avg output / run
63,500 tokens
Avg runtime / run
17m 11s
Avg quality
86.7
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 | 85.7 | 86.7 | 87.7 |
| Agent Workflow | 91.7 | 91.8 | 92.0 |
| Code Generation | 73.9 | 75.2 | 76.5 |
| Role Play & Narrative | 89.8 | 90.7 | 91.6 |
| Research & Analysis | 87.1 | 88.9 | 90.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination strata_ud-q4 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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XTX | llama.cpp | — | 59.4 tok/s | 59.0 tok/s | 124.0 GB | 196,608 tokens | 86.7 | 2 |
Benchmark runs
All 2 strata_ud-q4 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is strata_ud-q4 good for coding?
- In our benchmarks, strata_ud-q4 scores 75.2/100 for coding. It runs at about 59.0 tok/s, so if you want more speed, turbo is faster (~124.1 tok/s) and still scores well for coding (85.3/100).
- Is strata_ud-q4 good for agentic (tool-using) tasks?
- In our benchmarks, strata_ud-q4 scores 91.8/100 for agentic workflows. It runs at about 59.0 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is strata_ud-q4 for local inference?
- Across 2 community benchmark runs, strata_ud-q4 reaches up to 59.4 tok/s and averages 59.0 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
- How much memory does strata_ud-q4 need?
- The leanest observed configuration used about 124.0 GB of memory.
- Which tools have been used to run strata_ud-q4?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.