Model benchmarks
Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp local LLM performance
As of October 2026, Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp runs at up to 46.4 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
46.4 tok/s
Average speed
40.5 tok/s
Avg PP
369.9 tok/s
Min memory
15.2 GB
Max context
65,536 tokens
Avg output / run
52,944 tokens
Avg runtime / run
22m 42s
Avg quality
85.8
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 | 83.2 | 85.8 | 88.5 |
| Agent Workflow | 87.5 | 88.9 | 90.4 |
| Code Generation | 81.8 | 84.2 | 86.5 |
| Role Play & Narrative | 79.5 | 85.8 | 92.1 |
| Research & Analysis | 84.0 | 84.4 | 84.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp 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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7800 XT | llama.cpp k8 v4 -1 budget | — | 46.4 tok/s | 46.4 tok/s | 17.3 GB | 65,536 tokens | 82.9 | 1 |
| AMD Radeon RX 7800 XT | OpenAI-compatible | — | 34.6 tok/s | 34.6 tok/s | 15.2 GB | 65,536 tokens | 88.8 | 1 |
Benchmark runs
All 2 Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp good for coding?
- In our benchmarks, Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp scores 84.2/100 for coding, currently the best-scoring model for coding that runs on consumer hardware (≤24 GB VRAM). It runs at about 40.5 tok/s, so if you want more speed, K2-Horizon-MoVA-36B-A4B-MLX-4bit is faster (~48.5 tok/s) and still scores well for coding (82.5/100).
- Is Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp scores 88.9/100 for agentic workflows. It runs at about 40.5 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 Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp for local inference?
- Across 2 community benchmark runs, Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp reaches up to 46.4 tok/s and averages 40.5 tok/s, with the fastest results on AMD Radeon RX 7800 XT.
- How much memory does Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp need?
- The leanest observed configuration used about 15.2 GB of memory.
- Which tools have been used to run Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp?
- Benchmarks were submitted using OpenAI-compatible, llama.cpp k8 v4 -1 budget. Results are community-contributed and updated as new runs arrive.