Swen 1.1 Architecture Matrix

Comprehensive architectural specifications, empirical benchmarks, and deployment trade-offs across the three official Swen models architected by Darsh Yadav.

FLAGSHIP GENERALIST

Swen-1.1-Instruct

High-efficiency language model for code generation, agentic tool use & workflows.

Primary BenchmarkHumanEval: 66.0% 🥇
Scale / Weights1.17 Billion (~2.34 GB BF16)
Context Window128,000 Tokens
Best for: Real-time coding assistants, tool calling, agentic loops, long-context parsing
View Model Suite
PURE MATH SPECIALIST

Swen-1-Math

Ultra-compact mathematical engine with autonomous symbolic scratchpads.

Primary BenchmarkMultiArith: 85.0% 🥇
Scale / Weights350 Million (~708 MB BF16 / FP32)
Context Window64,000 Tokens
Best for: On-device arithmetic, Olympiad math, financial calculation, pure CPU execution
View Model Suite
METACOGNITIVE REASONER

Swen-1.1-Thinking

Test-time deliberative reasoning engine for self-reflection & backward induction.

Primary BenchmarkGPQA Diamond: 39.4% 🥇
Scale / Weights1.17 Billion (~2.34 GB BF16)
Context Window128,000 Tokens
Best for: Complex combinatorial game theory, multi-step logic proofs, scientific deduction
View Model Suite
Scroll horizontally to inspect benchmark data
Feature / Evaluation Metric Swen-1.1-Instruct Swen-1-Math Swen-1.1-Thinking
Empirical Reasoning Benchmarks
HumanEval (Pass@1)Zero-shot Python code synthesis benchmark66.0% 🥇28.4%62.5%
GSM8K (Grade School Math)Multi-step word mathematical problems54.0%44.0% (at 350M)56.8% 🥇
MATH-500 (Olympiad-Level)Challenging competition-level high school math24.2%35.0% 🥇38.1% 🥇
MultiArith AccuracyDeterministic multi-step arithmetic correctness68.0%85.0% 🥇78.5%
GPQA DiamondGraduate-level scientific and mathematical reasoning38.0%22.4%39.4% 🥇
Game Theory & CombinatoricsBackward induction & impartial games (Nim, etc.)52.0%64.0%92.4% 🥇
Architecture & Formulation
Parameter ScaleTotal non-embedding trainable weights1.17 Billion350 Million1.17 Billion
Context WindowNative uncompressed token processing length128,000 Tokens64,000 Tokens128,000 Tokens
Neural BackboneCore attention and convolution formulationHybrid Double-Gated Conv + Linear GQALinear Causal ConvolutionsDeliberative Hybrid Conv + GQA
Scratchpad ProtocolIntermediate cognitive deliberation format<|tool_call_start|> Agent Protocol<|cot_start|> Algebraic Scratchpad<think> ... </think> Metacognitive CoT
KV-Cache Memory ComplexityScaling behavior across long document promptsO(1) Constant bounded bufferO(1) Strict linear streamingO(1) Bounded reflection cache
Weights FootprintDisk & RAM consumption in BF16 precision~2.34 GB~708 MB~2.34 GB
Hardware & Execution Profile
Time-to-First-Token (TTFT)Initial prompt processing and prefill response latency< 15 ms< 8 ms (Ultra-fast)~ 20 ms (Deliberation phase)
Decode ThroughputSustained generation speed (RTX 6000 Ada / M3 Max)80–90 tok/s140+ tok/s95 tok/s
Minimum System RAMRequired system memory for edge inference4 GB RAM1 GB RAM (Runs in L3 Cache)4 GB RAM
Optimal Silicon TargetRecommended deployment environmentMacBook, Laptops, Edge AI PCsPure CPU, Embedded Chips, Raspberry PiWorkstation GPUs, RTX, Cloud Instances
SORIKA RESEARCH PUBLICATION #002

Read the Full Swen 1.1 Technical Report

Authored by Darsh Yadav. Contains complete ablation studies on hybrid double-gated causal convolutions, test-time metacognitive reasoning, and exact benchmark reproductions.

Under Development