Qwen 3.5 35B-A3B (Unsloth)
Qwen 3.5 35B-A3B is a multimodal MoE model by Alibaba with 35 billion total and 3 billion active parameters on a hybrid architecture. This Q4 quantization by Unsloth enables efficient local operation; the context window spans 262,000 tokens. Features an optional thinking mode, native tool use, and vision capability via a separate multimodal projector file.
- Open Weights
- Workstation
- llama.cpp
- Text
- Instruction-Tuned
- Real-Time
Sovereign Risk: LOW Fully local inference without cloud connection. The weights are publicly available (Apache 2.0, Unsloth quantization) and run entirely locally. NSL is not relevant, as no data is transmitted to Alibaba or Unsloth infrastructure.
Key metrics
Score · Latency · Cost · Quality
- Total Score Silver
- 74.32
- Routine
- 45.5
- Reasoning
- 28.82
- LLM Judge Avg
- 3.72 / 5
- 100 Coverage
- Avg Task Duration
- 14.21s
- Real-Time
- Token Rate
- 69.34tok/s
- Output Rate
- P95 Latency
- 39.81s
- Top 5 %
- Total Tokens
- 64700
- Output Volume
- Cost per 1K
- $0
- USD / 1K Requests
- Benchmark Cost
- $0
- Total · 64700 tok
Benchmark modules
10 modules · weighted · vs. model median & top performer
Qwen 3.5 35B-A3B (Unsloth)
Best model
Ø All models
Code Quality
72.5
CLI Benchmark
91.67
Logical Reasoning
70.39
UX Writing
74.35
Documentation
70.58
Content Transform.
76.4
Cultural Intelligence
75.6
Synthesis Quality
55.83
Tool Execution
90
ToolUse Score
71.75
Benchmark Cost
$0
Token efficiency & latency
Consumption per module vs. model median
Token consumption per module
Performance profile
Key metrics – legend
Score
- Total Score
- Overall score derived from Routine and Reasoning scores. Basis for the fleet rank and tier assignment (Gold / Silver / Bronze).
- Routine
- Score for standard tasks: code generation, text transformation, structured outputs. Weighted by task complexity.
- Reasoning
- Score for analytical and logical tasks: multi-step problem solving, mathematical reasoning, structured argumentation.
- Rank
- Position in the fleet comparison, sorted by Total Score. Refers to the snapshot at the time of testing.
LLM Judge
- LLM Judge Ø
- Average quality rating by an independent judge model on a scale of 1–5.
- Coverage
- Share of tasks for which a judge rating is available. 100% means all responses were evaluated.
Latency & speed
- Avg. Task Duration
- Average time per task from the first to the last token of the response, measured across all benchmark tasks.
- Token Rate
- Output speed in tokens per second. Relevant for interactive applications and real-time streaming.
- P95 Latency
- 95th percentile of response times — shows outliers. Lower values mean fewer long wait times in edge cases.
Cost
- Cost per 1K
- API price per 1,000 output tokens in US dollars. Basis for cost calculation in production use.
- Benchmark Cost
- Total cost for the complete benchmark run of this model.