DeepSeek-V4.1-Flash (EXL3) (Thinking)
Eight of 552 billion backbone parameters active during reads, sixteen during writes: DeepSeek-V4.1-Flash shifts compute to where agents touch it most. This card describes a community quant as an EXL3 variant of the official MIT-licensed model from September 10, 2026 — multimodal for text and image, one million tokens of context, operable on shared server memory thanks to quantization.
- Open Weights
- Server
- vLLM
- Text
- Vision
- Long Context
- Speculative Decoding
- Community-Quantisierung
- Batch
Sovereign Risk: MEDIUM The model was developed by DeepSeek, a company based in China. The Chinese jurisdiction is subject to laws that may allow state access to data, which poses a high risk for cloud services. However, since this is an Open Weights model under an MIT license intended for local operation, the risk to the end user is significantly reduced. In a purely local deployment, no data is transmitted to the vendor or third parties. The ‘medium’ risk rating reflects the potential influence of the origin jurisdiction on training data and model development, while the direct data exfiltration risk in local use is assessed as low. Additionally, this is a community quant (re-quantization by a third party), not an official DeepSeek release; the provenance of the quant must be considered independently of the MIT-licensed original weights.
Key metrics
Score · Latency · Cost · Quality
- Total Score Silver
- 74.51
- Routine
- 45.23
- Reasoning
- 29.28
- LLM Judge Avg
- 3.65 / 5
- 100 Coverage
- Avg Task Duration
- 98.95s
- Batch
- Token Rate
- 30.46tok/s
- Output Rate
- P95 Latency
- 225.57s
- Top 5 %
- Total Tokens
- 174700
- Output Volume
- Cost per 1K
- $0
- USD / 1K Requests
- Benchmark Cost
- $0
- Total · 174700 tok
Benchmark modules
10 modules · weighted · vs. model median & top performer
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 / Standard).
- 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.