Model benchmarks
empero-ai/Qwen3.8-35B-A3B-Distill-GGUF local LLM performance
As of September 2026, empero-ai/Qwen3.8-35B-A3B-Distill-GGUF runs at up to 119.6 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
119.6 tok/s
Average speed
107.4 tok/s
Avg PP
969.5 tok/s
Min memory
1379.6 GB
Max context
262,144 tokens
Avg output / run
10,386 tokens
Avg runtime / run
1m 50s
Avg quality
83.6
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 | 83.3 | 83.6 | 84.0 |
| Agent Workflow | 81.7 | 83.9 | 86.0 |
| Code Generation | 76.1 | 76.9 | 77.7 |
| Role Play & Narrative | 86.3 | 87.9 | 89.5 |
| Research & Analysis | 84.3 | 85.9 | 87.5 |
Performance by hardware and tool
Every hardware/tool/quantization combination empero-ai/Qwen3.8-35B-A3B-Distill-GGUF has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XT/7900 XTX/7900M | Unsloth Studio | Q6_K | 119.6 tok/s | 107.4 tok/s | 1379.6 GB | 262,144 tokens | 83.6 | 2 |
Benchmark runs
All 2 empero-ai/Qwen3.8-35B-A3B-Distill-GGUF runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is empero-ai/Qwen3.8-35B-A3B-Distill-GGUF good for coding?
- In our benchmarks, empero-ai/Qwen3.8-35B-A3B-Distill-GGUF scores 76.9/100 for coding. It runs at about 107.4 tok/s, so if you want more speed, Qwen3.6-35B-A3B-Q4_K_XL is faster (~156.9 tok/s) and still scores well for coding (82.2/100).
- Is empero-ai/Qwen3.8-35B-A3B-Distill-GGUF good for agentic (tool-using) tasks?
- In our benchmarks, empero-ai/Qwen3.8-35B-A3B-Distill-GGUF scores 83.9/100 for agentic workflows. It runs at about 107.4 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-Q4_K_S is faster (~162.4 tok/s) and still scores well for agentic workflows (87.8/100).
- How fast is empero-ai/Qwen3.8-35B-A3B-Distill-GGUF for local inference?
- Across 2 community benchmark runs, empero-ai/Qwen3.8-35B-A3B-Distill-GGUF reaches up to 119.6 tok/s and averages 107.4 tok/s, with the fastest results on AMD Radeon RX 7900 XT/7900 XTX/7900M.
- How much memory does empero-ai/Qwen3.8-35B-A3B-Distill-GGUF need?
- The leanest observed configuration used about 1379.6 GB of memory (quantizations tested: Q6_K).
- Which tools have been used to run empero-ai/Qwen3.8-35B-A3B-Distill-GGUF?
- Benchmarks were submitted using Unsloth Studio. Results are community-contributed and updated as new runs arrive.