Model benchmarks
SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact local LLM performance
As of November 2026, SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact runs at up to 35.4 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
35.4 tok/s
Average speed
34.6 tok/s
Avg PP
219.0 tok/s
Min memory
7.1 GB
Max context
131,072 tokens
Avg output / run
18,281 tokens
Avg runtime / run
9m 3s
Avg quality
79.4
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 | 78.6 | 79.4 | 80.1 |
| Agent Workflow | 71.5 | 75.9 | 80.3 |
| Code Generation | 69.5 | 70.5 | 71.5 |
| Role Play & Narrative | 87.7 | 89.4 | 91.2 |
| Research & Analysis | 80.3 | 81.6 | 82.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3050 | llama.cpp | — | 35.4 tok/s | 34.6 tok/s | 7.1 GB | 131,072 tokens | 79.4 | 2 |
Benchmark runs
All 2 SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact good for coding?
- In our benchmarks, SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact scores 70.5/100 for coding. It runs at about 34.6 tok/s, so if you want more speed, nvidia/Qwen3.8-27B-NVFP4 is faster (~63.3 tok/s) and still scores well for coding (82.7/100).
- Is SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact good for agentic (tool-using) tasks?
- In our benchmarks, SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact scores 75.9/100 for agentic workflows. It runs at about 34.6 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 SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact for local inference?
- Across 2 community benchmark runs, SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact reaches up to 35.4 tok/s and averages 34.6 tok/s, with the fastest results on NVIDIA GeForce RTX 3050.
- How much memory does SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact need?
- The leanest observed configuration used about 7.1 GB of memory.
- Which tools have been used to run SC117/Qwen3_6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-I-Compact?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.