Model benchmarks
unsloth/Qwen3.5-9B-GGUF local LLM performance
As of November 2026, unsloth/Qwen3.5-9B-GGUF runs at up to 52.2 tok/s for local inference (best of 5 community benchmark runs across 3 GPUs).
Model size
9B
Peak speed
52.2 tok/s
Average speed
28.9 tok/s
Avg PP
620.9 tok/s
Min memory
8.1 GB
Max context
262,144 tokens
Avg output / run
8,930 tokens
Avg runtime / run
8m 38s
Avg quality
70.2
Benchmark runs
5
GPUs tested
3
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 5 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 | 65.7 | 70.2 | 73.7 |
| Agent Workflow | 46.8 | 67.5 | 80.1 |
| Code Generation | 50.2 | 58.9 | 65.1 |
| Role Play & Narrative | 70.2 | 75.6 | 80.3 |
| Research & Analysis | 74.8 | 78.6 | 82.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination unsloth/Qwen3.5-9B-GGUF 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 2070 | Unsloth Studio | Q4_K_M | 52.2 tok/s | 52.2 tok/s | 8.1 GB | 8,192 tokens | 74.1 | 1 |
| NVIDIA GeForce RTX 5050 Laptop GPU | Unsloth Studio | Q4_K_M | 50.9 tok/s | 50.9 tok/s | 8.6 GB | 32,768 tokens | 65.2 | 1 |
| Intel(R) Arc(TM) 140V GPU (16GB) | Unsloth Studio | UD-Q4_K_XL | 14.6 tok/s | 14.2 tok/s | 17.2 GB | 262,144 tokens | 72.0 | 2 |
| Intel(R) Arc(TM) 140V GPU (16GB) | llama.cpp | — | 13.3 tok/s | 13.3 tok/s | n/a | 16,384 tokens | 67.4 | 1 |
Benchmark runs
All 5 unsloth/Qwen3.5-9B-GGUF runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is unsloth/Qwen3.5-9B-GGUF good for coding?
- In our benchmarks, unsloth/Qwen3.5-9B-GGUF scores 58.9/100 for coding. It runs at about 28.9 tok/s, so if you want more speed, byteshape/Qwen3.8-27B-GGUF:IQ4_XS-ASCII-Condensed is faster (~42.0 tok/s) and still scores well for coding (86.3/100).
- Is unsloth/Qwen3.5-9B-GGUF good for agentic (tool-using) tasks?
- In our benchmarks, unsloth/Qwen3.5-9B-GGUF scores 67.5/100 for agentic workflows. It runs at about 28.9 tok/s, so if you want more speed, muse-glimmer:latest is faster (~33.3 tok/s) and still scores well for agentic workflows (91.6/100).
- How fast is unsloth/Qwen3.5-9B-GGUF for local inference?
- Across 5 community benchmark runs, unsloth/Qwen3.5-9B-GGUF reaches up to 52.2 tok/s and averages 28.9 tok/s, with the fastest results on NVIDIA GeForce RTX 2070.
- How much memory does unsloth/Qwen3.5-9B-GGUF need?
- The leanest observed configuration used about 8.1 GB of memory (quantizations tested: Q4_K_M, UD-Q4_K_XL).
- Which tools have been used to run unsloth/Qwen3.5-9B-GGUF?
- Benchmarks were submitted using Unsloth Studio, llama.cpp. Results are community-contributed and updated as new runs arrive.