Model benchmarks
Qwen3.6-35B-A3B-IQ4_NL local LLM performance
As of August 2026, Qwen3.6-35B-A3B-IQ4_NL runs at up to 169.5 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
169.5 tok/s
Average speed
167.2 tok/s
Min memory
17.1 GB
Max context
65,536 tokens
Avg output / run
15,223 tokens
Avg runtime / run
1m 32s
Avg quality
73.5
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 | 73.4 | 73.5 | 73.6 |
| Agent Workflow | 70.5 | 75.4 | 80.4 |
| Code Generation | 54.1 | 58.3 | 62.5 |
| Role Play & Narrative | 79.9 | 80.9 | 81.8 |
| Research & Analysis | 79.1 | 79.4 | 79.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.6-35B-A3B-IQ4_NL has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M | llama.cpp | — | 169.5 tok/s | 167.2 tok/s | 17.1 GB | 65,536 tokens | 73.5 | 2 |
Frequently asked questions
- Is Qwen3.6-35B-A3B-IQ4_NL good for coding?
- In our benchmarks, Qwen3.6-35B-A3B-IQ4_NL scores 58.3/100 for coding. It runs at about 167.2 tok/s, so if you want more speed, Gemma4:E2B/QAT-MTP@131K is faster (~303.9 tok/s) and still scores well for coding (66.9/100).
- Is Qwen3.6-35B-A3B-IQ4_NL good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.6-35B-A3B-IQ4_NL scores 75.4/100 for agentic workflows. It runs at about 167.2 tok/s, so if you want more speed, Gemma4:E2B/QAT-MTP@131K is faster (~303.9 tok/s) and still scores well for agentic workflows (71.7/100).
- How fast is Qwen3.6-35B-A3B-IQ4_NL for local inference?
- Across 2 community benchmark runs, Qwen3.6-35B-A3B-IQ4_NL reaches up to 169.5 tok/s and averages 167.2 tok/s, with the fastest results on AMD Radeon RX 7900 XT/7900 XTX/7900 GRE/7900M.
- How much memory does Qwen3.6-35B-A3B-IQ4_NL need?
- The leanest observed configuration used about 17.1 GB of memory.
- Which tools have been used to run Qwen3.6-35B-A3B-IQ4_NL?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.