Mixture-of-Experts (MoE) models are bottlenecked by loading routed-expert weights from memory during interactive decoding at small batch sizes. Because most intermediate channels in a routed expert contribute little to any single token, channel selectors predict which channels matter and read only their weights, typically keeping channels above a threshold calibrated on offline data. We show that channel selection needs no calibration data. First, a calibrated threshold does not fix how much a selector reads, because the number of channels passing it varies across inputs; Prox with thresholds calibrated for an 18% read budget actually reads only 12.9% on average across our benchmarks. Second, top-k keeps each token's k highest-scoring channels and needs no calibration data. At the calibrated budget, a selector's top-k version matches or beats its threshold version on the same score in 40 of 43 comparisons at 13% and 18% budgets, including all 23 on generation tasks. The top-k versions also avoid the repetition-loop collapse that calibrated thresholds cause on Gemma 4. Calibrating a threshold thus provides neither of the two things selectors use it for: a known read budget and a consistent accuracy gain at that budget. We furthermore introduce a reader built entirely from the model's weights, which screens channels with a ternary sketch and recovers the skipped ones with a low-rank map. Across three post-trained MoE models, our reader retains 98.1% of full-model accuracy at 17.8% of routed-expert reads, with Triton kernels running MoE blocks 1.60 to 1.90x faster than optimized vLLM at batch one and up to 2.69x at larger batches on the same three models.
Figures & tables
Figure 1: At heavy sparsity, calibrated selectors lose most of their accuracy on at least one task, whereas data-free top- k selectors stay accurate and our reader performs best and decodes faster. (a) Worst accuracy over three MoE models and three benchmarks; dashed lines use calibrated thresholds, placed at the budget they were calibrated for. See Appendix Figure 11 for the same curves with calibrated selectors placed at the reads they actually used. (b) Whole-model decoding speedup of our reader at 17.8% of reads over optimized vLLM.
Figure 2: A channel selector computes only a subset of each routed expert’s channels, and hardware charges every 32-byte sector it touches. (a) Channel j owns row j of the gate and up projections ( Ge,Ve ) and column j of the down projection ( De ); H is the hidden width, I the number of channels per expert, ϕ the gate activation. (b) On the same scores, a calibrated threshold τ keeps six channels on token A and two on token B, while top- k keeps four on both. (c) A selector that needs 80 bytes spread over four sectors is charged 128 bytes.
Figure 3: Prior channel selectors, grouped by what they read before choosing channels. Dashed rows or columns are skipped; chips show each keep rule, and a dot marks budgets or rotations fitted on data. HiRE and Mixture-of-Channels (MoC) train the model for top- k ; TopK-Guided bounds a threshold by a top- k window. Our reader (bold) fits nothing to the model.
Figure 4: Under a calibrated threshold, the number of kept channels changes from token to token, and selectors read less than their budget on benchmarks. (a) Share of channels each token keeps under an exact-score threshold calibrated on UltraChat for about 12%, on held-out chat and on the model’s answers to GPQA-Diamond ( Rein et al., 2024 ) , IFEval ( Zhou et al., 2023 ) , and MMLU-Pro ( Wang et al., 2024 ) ; top- k keeps the same share on every token (line). (b) Median kept count per 500-token window, relative to the calibrated count (about 94,000 answer tokens per model). (c) In all 72 benchmark runs, Prox and our reader with calibrated thresholds read below their budget (the diagonal).
Figure 5: On the same score, a selector’s top- k version matches or beats its threshold version in 40 of 43 comparisons and avoids Gemma 4’s collapse. Each dot is the accuracy of a selector’s threshold version minus that of its top- k version, at the budget the threshold was calibrated for, with ±2 paired SE. Gray marks ties, blue top- k leads (the four on Gemma 4 by 38 to 45 points), and orange threshold leads (at most 2.8 points). See Appendix Figure 8 for the same comparisons with each top- k version run at the reads its threshold version actually used.
Figure 6: Our reader screens candidate channels with a ternary sketch, computes the top- k channels exactly, and recovers the rest using only the full model’s weights. Top: the full model reads every channel of a routed expert; our reader reads a ternary sketch, the k kept channels, and a low-rank recovery map. Middle: the three stages. Bottom: reads at 17.8% on Qwen3-Thinking.
About 13% of reads
About 18% of reads
Selector
Target
Realized
Mean
Worst
Target
Realized
Mean
Worst
Our reader
–
12.8
94.5
86.9
–
17.8
98.1
95.0
Prox score, top- k
–
13.5
87.0
61.1
–
18.5
96.1
90.4
Prox as published, calibrated
13
8.5
51.5
0.0
18
12.9
68.5
12.1
WINA as published, top- k
–
15
2.4
0.0
–
20
28.4
1.1
WINA score, calibrated
15
7.8
0.2
0.0
20
11.2
5.0
0.0
Table 1: Our reader is the most accurate tested selector at the two lowest budgets. Mean and worst accuracy over nine model-benchmark pairs, as a percentage of the full model’s accuracy. Selectors with calibrated thresholds list the budget they were calibrated for (Target) and the reads they used (Realized); WINA as published uses top- k and meets its budget to the precision shown.
Figure 7: Our reader accelerates MoE blocks by 1.60 to 2.69 × over optimized vLLM across three post-trained models. At 17.8% of routed-expert reads, median of three processes. (a) MoE-block decode speedup; both arms share the unmodified router, and Gemma 4’s dense MLP and Qwen3.5’s shared expert are timed inside the block. (b) Whole model, batch sizes 1 to 128: right is faster per user, up is more output per GPU.
Appendix figures & tables24 assets
Supplementary material from the paper’s appendix.
Appendix
Study
Regime
Models
Same score
Matched
Ahead
La RoSA ( 2025b )
dense, PPL
LLaMA2-7B
yes
target
top- k (PPL)
Batch-wise pruning ( 2026c )
dense, CoT
2 distilled 7–8B
yes
target
top- k (batch 4)
Sparsing Law ( 2025 )
dense, short tasks
0.1B, 0.8B
no
target
threshold
Prox ( 2026 )
dense, short tasks
Qwen3-8B, 14B
yes
target
threshold (+1.8)
TopK-Guided ( 2026 )
dense, short tasks
Llama-2/3, 7–8B
no
target
hybrid; top- k vs. τ mixed
Sparser-MoE ( 2026d )
MoE, short tasks
OLMoE
unclear
target
top- k ( < 1 pt)
Appendix
Table 2: Prior keep-rule comparisons reach opposite conclusions, focus mostly on short tasks on dense models, and none runs top- k at the reads a threshold actually uses. Unlike most prior comparisons, ours holds the channel score fixed ( Same score ), tests long chain-of-thought reasoning on MoE models ( Regime ), and runs top- k both at the target budget and at realized reads ( Matched ).
Routed experts
Width
MoE
Always
Added memory (%)
Model
Total
Active
Expert
Hidden
layers
full
Sketch
Recovery
Qwen3-Thinking
128
8
768
2048
48
–
7.6
0.50
Gemma 4
128
8
704
2816
30
dense MLP
7.0
0.35
Qwen3.5
256
8
512
2048
40
shared expert
7.0
0.47
OLMoE
64
8
1024
2048
16
–
7.3
0.50
Appendix
Table 3: Evaluated MoE models and the resident memory our reader adds. Each row gives the number of routed experts and how many each token uses, the channels per expert and the hidden width, the number of MoE layers, any module that always runs in full, and the resident memory of our reader’s ternary sketch and recovery map as a percentage of the BF16 checkpoint. OLMoE’s sketch size is computed analytically.
Sampling
Model
Benchmark
Items
Samples
Temperature
Top- p
Top- k
Max tokens
Qwen3-Thinking
GPQA-D
198
4
0.6
0.95
20
32,768
IFEval
541
1
0.6
0.95
20
32,768
MMLU-Pro
1,000
1
0.6
0.95
20
32,768
Gemma 4
GPQA-D
198
4
1.0
0.95
64
32,768
IFEval
541
1
1.0
0.95
64
32,768
Appendix
Table 4: Evaluation protocol on the post-trained models. Each model runs in thinking mode with its model card’s sampling parameters and random seed 20260923. GPQA-Diamond reports accuracy over four samples per question, IFEval reports prompt-level strict accuracy, and MMLU-Pro reports accuracy on a fixed 1,000-question subset.
Routed-expert reads (%)
Model
Sketch read
Sketch
Exact channels
Recovery
Metadata
Total
Qwen3-Thinking
partial
4.86
7.29
0.66
0.04
12.85
partial
4.86
12.30
0.63
0.04
17.83
full
7.99
20.00
0.59
0.10
28.68
full
7.99
30.00
0.54
0.10
38.62
Gemma 4
partial
4.78
7.49
0.54
0.03
12.84
Appendix
Table 5: Most of our reader’s reads go to exact channels, and the sketch takes most of the rest. Routed-expert reads per token at batch one, as a percentage of the full model, by component at the four main budgets. At the two smallest budgets, the partial screen reads part of the ternary sketch.
Sketch read
partial
partial
full
full
full
full
Channels computed exactly (%)
7.0–7.5
12.0–12.5
20
30
50
70
Reads (% of full model)
12.8
17.8
28.7
38.7
58.6
78.5
Appendix
Table 6: Our reader reads part of the sketch at the two smallest budgets and all of it above. Each column is one budget. It gives the share of candidate channels computed exactly across each token’s routed experts and the resulting total reads, which include the ternary sketch, exact channels, recovery map, and metadata, averaged over the three post-trained models and three benchmarks.
Batch size
1
4
8
Full model
75.6
229.1
359.3
Our reader
13.9
49.9
92.3
Share
18.3%
21.8%
25.7%
Appendix
Table 7: At batch one, the profiler measures 18.3% of the full model’s DRAM reads, close to the 17.8% we count. Measured DRAM reads per MoE layer on Qwen3-Thinking in MB, averaged over 12 layers, without the router, with a cold cache.
Realized reads (%)
Method
Calibrated for (%)
Min
Mean
Max
CATS
53.3
51.1
52.1
53.0
66.7
63.8
65.1
66.0
Our reader, calibrated
12.8
11.2
11.8
12.4
17.8
15.2
16.5
17.1
28.7
24.5
26.5
27.7
Appendix
Table 8: Every calibrated threshold reads less than the budget it was calibrated for. Each row is one selector at one calibrated budget. The columns give the lowest, mean, and highest realized routed-expert reads (%) over the nine model-benchmark pairs.
Context before the window
Kept channels
Change
Question and all 6,000 earlier answer tokens
9,983
–
Question and the last 1,000 answer tokens
11,423
+15.0
±1.2%
Question only
15,422
+56.6
±2.7%
Start of the answer (different tokens)
17,283
Appendix
Table 9: The same tokens keep more channels when the earlier answer is removed. The first three rows change only the context before the 256-token windows at answer position 6,000 of Qwen3-Thinking GPQA-Diamond traces, under Prox’s threshold calibrated for 13%. Kept channels are per token, summed over 48 layers (of 294,912 candidates) and averaged over 48 traces; ± is one paired SE. The last row shows the start of the answer, which has different tokens.
Model
Task
Score
Budget (%)
τ
k
τ−k
Gemma 4
GPQA-D
Prox, output-scaled
13
16.2
54.0
−37.9
±3.8
k
Prox
13
6.1
51.0
−44.9
±3.5
k
IFEval
Prox, output-scaled
13
23.1
63.6
−40.5
±2.3
k
Prox
13
3.5
45.8
−42.3
±2.2
k
TEAL
18
0.0
7.0
−7.0
±1.1
–
OLMoE
BBH
Prox, output-scaled
13
25.4
26.1
−0.7
±0.6
=
Appendix
Table 10: Keep-rule comparisons on generation tasks. Each row fixes one model, task, score, and budget. It gives the accuracy of the threshold version ( τ ) and the top- k version ( k ), their paired difference ± one standard error, and which version is ahead ( = within two standard errors, – both collapsed).
Model
Task
Score
Budget (%)
τ
k
τ−k
Gemma 4
GPQA-D
Prox, output-scaled
13
16.2
30.3
−14.1
±3.5
k
Prox
13
6.1
24.2
−18.2
±2.9
k
IFEval
Prox, output-scaled
13
23.1
34.0
−10.9
±2.1
k
Prox
13
3.5
16.5
−12.9
±1.6
k
TEAL
18
0.0
0.2
−0.2
±0.2
–
OLMoE
BBH
Prox, output-scaled
13
25.4
25.3
+0.1
±0.6
=
Appendix
Table 11: The generation-task comparisons with each top- k version run at its threshold version’s realized reads. Columns follow Table 10 . The top- k version is rerun only where the threshold version’s realized reads differ from the budget by more than one percentage point. † The threshold version read within one point of its budget, so the top- k run at the budget is reused.
Prompt
Task
Budget (%)
τ
k
τ−k
full model
ARC-C
13
49.7
50.0
−0.3
±0.9
=
ARC-E
13
73.9
73.2
+0.7
±0.6
=
HellaSwag
13
75.4
74.9
+0.6
±0.3
τ
MMLU
13
50.3
50.3
−0.0
±0.3
=
PIQA
13
77.7
76.4
+1.3
±0.7
=
ARC-C
18
51.9
51.4
+0.5
±0.9
=
Appendix
Table 12: Keep-rule comparisons on Prox’s five likelihood tasks on OLMoE. Prox’s threshold and top- k versions, with the prompt either sparse or computed by the full model. Columns follow Table 10 . At 38%, the top- k version keeps 50% of inputs and the threshold version 30%; these verdicts are in parentheses and not counted.
Prompt
Task
Budget (%)
τ
k
τ−k
full model
ARC-C
13
49.7
50.0 †
−0.3
±0.9
=
ARC-E
13
73.9
73.2 †
+0.7
±0.6
=
HellaSwag
13
75.4
74.9 †
+0.6
±0.3
τ
MMLU
13
50.3
49.7
+0.5
±0.3
=
PIQA
13
77.7
76.4 †
+1.3
±0.7
=
ARC-C
18
51.9
52.8
−0.9
±0.9
=
Appendix
Table 13: The likelihood-task comparisons with each top- k version run at its threshold version’s realized reads. Columns follow Table 10 . † The threshold version read within one point of its budget, so the top- k run at the budget is reused.
At the calibrated budget
At realized reads
Model
Comparisons
τ−k
Comparisons
τ−k
Qwen3-Thinking
4
−0.3
±1.0
4
+4.5
±1.1
Qwen3.5
3
−1.7
±0.7
2
−0.2
±0.8
OLMoE
32
−0.3
±0.1
31
+0.0
±0.1
Gemma 4
4
−41.5
±1.3
4
−13.3
±1.1
Appendix
Table 14: No model favors the threshold version at the calibrated budget. Threshold-version minus top- k -version accuracy, pooled over each model’s counted comparisons with inverse-variance weights, at the calibrated budget and at realized reads. The ± is one SE that treats comparisons as independent; accounting for shared questions changes each SE by at most 0.1. The realized-read columns favor the threshold version (Section 2 ). Only Qwen3-Thinking leads beyond two SE there, a lead that comes from Prox on IFEval and reverses at the calibrated budget.
Figure 8: Figure 5 with each top- k version run at the reads its threshold version actually used. Each dot is one comparison, as in Figure 5 . When a threshold version read more than one percentage point away from its calibrated budget, the top- k version is rerun at those realized reads. The figure has 41 comparisons at 13% and 18% budgets; four TEAL comparisons at heavy sparsity, where both versions collapse, are left out. Threshold versions read less than their budget, so this rerun lowers the top- k version’s reads too, yet the top- k version matches or beats the threshold version in 37 of 41.
Task
Shots
Metric
Questions
Full model (%)
MMLU
5
accuracy
14,042
52.71
HellaSwag
10
normalized accuracy
10,042
79.40
ARC-E
0
accuracy
2,376
78.11
ARC-C
25
normalized accuracy
1,172
55.20
PIQA
0
accuracy
1,838
79.98
Appendix
Table 15: Prox’s five likelihood tasks on OLMoE. Few-shot examples, metric, number of questions, and full-model accuracy for each task.
Reads (%)
13.5
18.5
28.5
38.4
Full sketch, no recovery
0.553
0.277
0.107
0.051
Full sketch with recovery
0.488
0.245
0.096
0.047
Partial sketch with recovery
0.310
0.187
0.090
0.053
Prox’s 4-bit copy, output-scaled top- k , recovery
0.305
0.187
0.070
0.035
Appendix
Table 16: Partial screening helps at small budgets, and recovery helps at every budget. Next-token KL divergence from the full model on held-out OLMoE documents at equal reads (lower is better). Each row is one variant of our reader.
Variant at 17.8% of reads (OLMoE, development)
KL
Full sketch, no recovery (rotated, top- k over all routed experts)
0.286
Without rotation
0.348
Fixed share of channels per expert
0.491
Score from an INT4 copy of the gate projection, same top- k
0.811
Score from TEAL’s input magnitudes, top- k inputs
1.471
Appendix
Table 17: Rotation and ranking channels across all routed experts lower KL divergence, and reading 80 of 128 coordinates is at or near the best. Next-token KL divergence from the full model on development data (lower is better). Top: at 17.8% of reads on OLMoE without recovery, the full sketch, two of its design variants, and two other scores under top- k . Bottom: coordinates the partial screen reads per 128-coordinate block, with recovery, at equal reads; bold marks the lowest in each row.
Figure 9: Accuracy against reads on every model and task. Each panel is one model-benchmark pair, and its vertical axis runs from zero to above the full model’s accuracy (dotted line). Blue solid lines use no calibration data. Warm dashed lines are selectors with thresholds fitted on calibration data, placed at the budget they were calibrated for. WINA as published (red solid) keeps a top- k per token, with a sparsity level for each projection fitted on calibration data as in TEAL. GPQA-Diamond averages four samples per question, IFEval reports prompt-level strict accuracy, and MMLU-Pro uses a fixed subset of 1,000 questions.
Figure 10: Figure 9 with calibrated selectors placed at the reads they actually used. Selectors with calibrated thresholds move left, because they read less at test time than the budget they were calibrated for.
Figure 11: Figure 1 with calibrated selectors placed at the reads they actually used. Each curve is the worst accuracy over the nine model-benchmark pairs, as in Figure 1 , but each calibrated selector sits at the mean reads it used on the pair that gives its worst accuracy, instead of the budget it was calibrated for. Selectors with calibrated thresholds read less than that budget (Section 4.1 ), so their points move left.
Method
Budget (%)
GPQA-D
IFEval
MMLU-Pro
Qwen3-Thinking
Full model
100
70.8
87.8
80.5
Our reader
12.8
63.8
85.0
76.9
17.8
67.3
87.2
78.2
28.7
67.9
85.4
78.6
38.7
70.8
86.1
80.3
Appendix
Table 18: Accuracy of every selector on every model and task. Scores in percent at heavy sparsity. Budget is the mean reads for selectors without calibration data and the calibrated budget for the others. GPQA-Diamond (GPQA-D) averages four samples per question.
Budget
Method
Reads (%)
KL ( ↓ )
Top-1 ( ↑ )
∼13%
Our reader
12.8
0.334
0.751
Prox, calibrated, division tuned on development data
13.2
0.488
0.709
Prox as published, calibrated
13.7
0.462
0.723
HiRE-style gate screen
12.8
1.709
0.469
∼18%
Our reader
17.8
0.199
0.808
Prox, calibrated, division tuned on development data
18.3
0.298
0.774
Appendix
Table 19: On OLMoE, our reader is closer to the full model than every baseline evaluated at each budget. Next-token KL divergence from the full model (lower is better) and top-1 agreement on 192 held-out Pile documents, at the reads each method realizes. HiRE-style screens channels with an INT4 copy of the gate projection under our top- k . R-Sparse adds a low-rank term for skipped inputs. CHESS, CATS, M-COUNTDOWN (the up-projection variant of COUNTDOWN ( Cheon & Kang, 2025 ) ), and Park et al. (2026) compute one projection in full before thresholding, so they read at least a third of each routed expert.
Batch size
1
2
4
8
16
32
64
128
Qwen3-Thinking
MoE block (ms)
Full model
3.084
5.525
8.517
11.969
18.370
Our reader
1.619
2.604
3.562
5.131
9.260
not measured
Speedup ( × )
1.90
2.12
2.39
2.33
1.98
Per output token (ms)
Full model
6.253
9.454
12.450
15.666
22.044
27.366
34.107
38.196
Our reader
4.605
6.609
7.453
8.957
12.850
19.831
28.925
38.363
Appendix
Table 20: Speedups peak at batch sizes four to sixteen, and the whole-model gain fades by batch 128. Decode times at 17.8% of routed-expert reads, in milliseconds per decoding step, median of three processes. The MoE block covers all MoE layers with the router, Gemma 4’s dense MLP, and Qwen3.5’s shared expert. Whole-model times use 128-token prompts.
Figure 12: Our reader raises per-GPU throughput at the same per-user speed. Whole-model decoding of three post-trained models at 17.8% of routed-expert reads, against optimized vLLM, from Table 20 (128-token prompts, one RTX PRO 6000 Blackwell GPU). Each point is one batch size, labeled for our reader. Per-user speed is the inverse of the time per output token, and per-GPU throughput is the batch’s total output rate.
Mixture of Experts (MoE) models enable parameter-efficient scaling through sparse expert activations, yet optimizing their inference and memory costs remains challenging due to limited understanding of their specialization behavior. We present a systematic analysis of expert specialization in MoEs through two complementary approaches: domain-specific routing patterns and an early decoding framework that tracks expert contributions to output representations. Our analysis of the DeepSeekMoE model reveals that despite having 64 routed experts with 6 active for each layer's computation, the model predominantly relies on a few specialized experts, with the top-weighted expert's output closely approximating the full ensemble prediction. We quantitatively validate these findings through a systematic analysis of the token routing distribution, demonstrating that very few experts handle over 50% of routing decisions across different specialized domains. Hidden state similarity between single and ensemble experts for every layer is extremely high, with some layers having cosine similarity as high as 0.95 and perplexity increasing by only 5% when using a single expert across all three domains. Our results indicate that Mixture of Experts models exhibit concentrated expertise highlighting potential opportunities for inference optimization through targeted expert pruning while maintaining model performance and opening avenues towards studying localization of learned knowledge in these models.
The Pennsylvania State University, University Park, PA 16802 USA · University of Maryland, College Park, MD 20742 USA · Harvard University, Cambridge, MA 02138 USA
Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferring model weights from accelerator high-bandwidth memory into on-chip SRAM. Mixture-of-experts (MoE) models reduce computation by activating only a small subset of experts per token, but this sparsity does not translate directly to batched decoding. Different requests select different experts; therefore, the combined active set across many concurrent requests can span a substantial fraction of the expert pool and require significantly more expert weights to be transferred. Most expert-reduction techniques make retention decisions independently for each token and therefore do not address this batch-level expansion. More recently, batch-aware methods have attempted to coordinate expert use across concurrent requests and reuse experts already fetched for the batch. Yet their selection criteria are based primarily on router rankings or expert statistics collected during calibration. Consequently, these criteria are not directly tied to the output error caused by dropping an expert, nor do they capture how an expert's contribution changes across tokens at inference time. We instead rank experts according to how much their removal would change the MoE-layer output. To apply this criterion during serving, we train a lightweight linear predictor during calibration that estimates the expert removal cost for each incoming token, and develop custom GPU kernels for cost prediction and expert selection. Across three MoE architectures, BASE improves the quality-efficiency tradeoff without retraining. On Qwen3-30B-A3B, it improves average accuracy by 29.5 points over the strongest baseline at comparable throughput under a tight expert budget. At a higher expert budget, it is 60% faster than dense inference while remaining within 0.4 accuracy points.
Ali Abbasi, Justin Shi, Soheil Kolouri
College of Connected Computing, Vanderbilt University
Mixture-of-Experts (MoE) models reduce computation through sparse expert activation, but deployment still requires storing a large number of expert parameters. We study post-training expert pruning using task-domain calibration data as a subset-selection problem: given a pretrained MoE layer, select a fixed number of experts that best reconstruct its original output. Exact subset search is combinatorial and becomes intractable for modern MoE models with many experts per layer. We develop OptEP, a scalable continuous relaxation that directly optimizes differentiable expert-selection variables, followed by a lightweight reconstruction-based update of the retained expert weights. Across multiple MoE architectures and tasks spanning mathematical reasoning and code generation, our approach improves over the strongest existing expert-pruning baselines, with absolute accuracy gains of up to 15.05% on Qwen3-30B-A3B, 14.55% on Qwen3-235B-A22B, 11.06% on GLM-4.5-Air, and 16.20% on Mixtral-8x7B. The improvements are particularly pronounced under aggressive pruning, demonstrating that reconstruction-driven expert selection and weight adaptation can preserve substantially more of the original model's performance while reducing the number of retained experts.
Jelena Markovic-Voronov, Petros Prastakos, Kayhan Behdin +7